{"data":[{"id":"ripple-65b-preview","name":"ricursiveAI/Ripple-65B-Preview","created":1793818990,"description":"Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.23068672,"max_completion_cost":0.08650752,"max_cost":0.2883584},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0,"max_prompt_cost":287.38486580552967,"max_completion_cost":107.76932467707363,"max_cost":359.2310822569121},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"ricursiveai/ripple-65b-preview-20261104","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"hy4","name":"Tencent: Hy4","created":1793766031,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.587e-7,"completion":1.3755500000000001e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.3100000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.4809818112,"max_completion_cost":0.09014804480000001,"max_cost":0.5410684928},"sats_pricing":{"prompt":0.000571439213947801,"completion":0.0017136324629297966,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000028777514371471993,"input_cache_write":0.0,"max_prompt_cost":599.1974452045293,"max_completion_cost":112.30461709056715,"max_cost":674.0522219698134},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy4-20261104","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"glm-5.3-flashx-legal","name":"Z.ai: GLM 5.3 FlashX Legal","created":1793626154,"description":"GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.0700000000000003e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.42677043200000003,"max_completion_cost":0.18022400000000002,"max_cost":0.5536481280000001},"sats_pricing":{"prompt":0.0005070323960687923,"completion":0.0017129472840161902,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001027768370409714,"input_cache_write":0.0,"max_prompt_cost":531.6620017402299,"max_completion_cost":224.51942641057008,"max_cost":689.7236779332712},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flashx-legal-20261102","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"particle-1","name":"Particle AI: Particle-1","created":1793207893,"description":"Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-9,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.0720896,"max_cost":0.12255232},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.111073481638856e-6,"input_cache_write":0.0,"max_prompt_cost":71.84621645138242,"max_completion_cost":89.80777056422802,"max_cost":152.67320995918763},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"particle-ai/particle-1-20261027","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"high"}},{"id":"gpt-6.1-terra-pro","name":"OpenAI: GPT-6.1 Terra Pro","created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0017129472840161902,"max_prompt_cost":1438.8757185735994,"max_completion_cost":877.0290094162893,"max_cost":2140.4989261066307},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-terra-pro-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-6.1-terra-pro:batch","name":"OpenAI: GPT-6.1 Terra Pro (batch)","created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":6.875000000000001e-7,"max_prompt_cost":0.5775,"max_completion_cost":0.35200000000000004,"max_cost":0.8591},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000342589456803238,"input_cache_write":0.0008564736420080951,"max_prompt_cost":719.4378592867997,"max_completion_cost":438.51450470814467,"max_cost":1070.2494630533154},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-terra-pro-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-6.1-terra","name":"OpenAI: GPT-6.1 Terra","created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0017129472840161902,"max_prompt_cost":1438.8757185735994,"max_completion_cost":877.0290094162893,"max_cost":2140.4989261066307},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-terra-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-6.1-terra:batch","name":"OpenAI: GPT-6.1 Terra (batch)","created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":6.875000000000001e-7,"max_prompt_cost":0.5775,"max_completion_cost":0.35200000000000004,"max_cost":0.8591},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000342589456803238,"input_cache_write":0.0008564736420080951,"max_prompt_cost":719.4378592867997,"max_completion_cost":438.51450470814467,"max_cost":1070.2494630533154},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-terra-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"kimi-k3.1-pro","name":"MoonshotAI: Kimi K3.1 Pro","created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":2.3068672,"max_completion_cost":10.380898000000002,"max_cost":10.611585600000002},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":2873.8486580552967,"max_completion_cost":12932.313479817529,"max_cost":13219.699441909319},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k3.1-pro-20261023","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","created":1792379569,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.34603008,"max_cost":0.4325376},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000020555367408194277,"input_cache_write":0.0,"max_prompt_cost":215.53864935414725,"max_completion_cost":431.0772987082945,"max_cost":538.8466233853682},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":524288,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m3.1-flash-20261019","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"max"}},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-9,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.25952256,"max_cost":0.36765696000000003},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.111073481638856e-6,"input_cache_write":0.0,"max_prompt_cost":215.53864935414725,"max_completion_cost":323.30797403122085,"max_cost":458.0196298775629},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4.1-flash-20261017","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"glimpse","name":"Elorian: Glimpse","created":1792206629,"description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.8448,"max_cost":0.84885504},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008222146963277711,"input_cache_write":0.0,"max_prompt_cost":215.53864935414725,"max_completion_cost":1052.4348112995472,"max_cost":1057.4864983937848},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":256000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"elorian/glimpse-20261016","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","created":1792160499,"description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.2883584,"max_completion_cost":0.1441792,"max_cost":0.39649280000000003},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0,"max_prompt_cost":359.2310822569121,"max_completion_cost":179.61554112845604,"max_cost":493.94273810325416},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"reflection/beam-1.0-501b-a23b-20261016","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"max"}},{"id":"mercury-3","name":"Inception: Mercury 3","created":1792158337,"description":"Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":3.85e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.11,"max_completion_cost":0.05046272,"max_cost":0.1460448},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0004796252395245332,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.0,"max_prompt_cost":137.0357827212952,"max_completion_cost":62.865439394959616,"max_cost":181.9396680034092},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inception/mercury-3-20261019","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"}},{"id":"ternary-bonsai-2-9b","name":"PrismML: Ternary Bonsai 2 9B","created":1792130995,"description":"Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":8.800000000000001e-8,"completion":1.4300000000000002e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.023068672000000002,"max_completion_cost":0.009371648000000002,"max_cost":0.026673152000000006},"sats_pricing":{"prompt":0.00010962862617703617,"completion":0.00017814651753768378,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000054814313088518084,"input_cache_write":0.0,"max_prompt_cost":28.73848658055297,"max_completion_cost":11.675010173349644,"max_cost":33.22887510876437},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"prism-ml/ternary-bonsai-2-9b-20261015","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"moondream3-preview","name":"Moondream: Moondream 3 Preview","created":1792102385,"description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","context_length":32000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.01056,"max_completion_cost":0.011264000000000001,"max_cost":0.020472320000000002},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.155435141244338,"max_completion_cost":14.03246415066063,"max_cost":25.504003593825693},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moondream/moondream3-preview-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"moondream3.1-9b-a2b","name":"Moondream: Moondream 3.1","created":1792102373,"description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","context_length":32000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.01056,"max_completion_cost":0.011264000000000001,"max_cost":0.020472320000000002},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.155435141244338,"max_completion_cost":14.03246415066063,"max_cost":25.504003593825693},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moondream/moondream3.1-9b-a2b-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"muse-spark-open","name":"Meta: Muse Spark Open","created":1792087069,"description":"Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":4.675e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":1.4417920000000002,"max_completion_cost":4.41188165,"max_cost":4.5560614},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.0058240207656550455,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":1796.1554112845606,"max_completion_cost":5496.233228922448,"max_cost":5675.849455229818},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-open-20261015","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.5190449,"max_cost":0.53634647},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027407156544259042,"input_cache_write":0.0,"max_prompt_cost":215.53864935414725,"max_completion_cost":646.6156739908763,"max_cost":668.1696211477606},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3.5-super-vl-20261015","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"pareto-26.10","name":"Pareto 26.10","created":1792073620,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":3.52e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.92274688,"max_completion_cost":0.46137344,"max_cost":1.26877696},"sats_pricing":{"prompt":0.0010962862617703616,"completion":0.004385145047081446,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":1149.5394632221187,"max_completion_cost":574.7697316110593,"max_cost":1580.616761930413},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"unbiased/pareto-26.10-20261015","alias_ids":null,"forwarded_model_id":null},{"id":"pareto-latest","name":"Pareto Latest","created":1791933050,"description":"This model always redirects to the latest model in the Pareto family.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":3.52e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.92274688,"max_completion_cost":0.46137344,"max_cost":1.26877696},"sats_pricing":{"prompt":0.0010962862617703616,"completion":0.004385145047081446,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":1149.5394632221187,"max_completion_cost":574.7697316110593,"max_cost":1580.616761930413},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~unbiased/pareto-latest","alias_ids":null,"forwarded_model_id":null},{"id":"pareto-26.9","name":"Pareto 26.9","created":1791930537,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.7208960000000001,"max_completion_cost":1.081344,"max_cost":1.4417920000000002},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.010277683704097141,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":898.0777056422803,"max_completion_cost":1347.1165584634205,"max_cost":1796.1554112845606},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"unbiased/pareto-26.9-20260917","alias_ids":null,"forwarded_model_id":null},{"id":"lfm-2.5-24b-a2b","name":"LiquidAI: LFM2.5-24B-A2B","created":1791912025,"description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":7.7e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.00704,"max_completion_cost":0.00630784,"max_cost":0.01289728},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.0009592504790490664,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000342589456803238,"input_cache_write":0.0,"max_prompt_cost":8.770290094162892,"max_completion_cost":7.858179924369952,"max_cost":16.067171452506418},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"liquid/lfm-2.5-24b-a2b-20261012","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gemini-4-argon","name":"Google: Gemini 4 Argon","created":1791907477,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":2.2e-6,"web_search":0.015400000000000002,"internal_reasoning":0.000011000000000000001,"input_cache_read":1.1e-7,"input_cache_write":2.0625e-7,"max_prompt_cost":2.3068672,"max_completion_cost":10.380898000000002,"max_cost":10.611585600000002},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.002740715654425904,"web_search":19.18500958098133,"internal_reasoning":0.013703578272129521,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0002569420926024285,"max_prompt_cost":2873.8486580552967,"max_completion_cost":12932.313479817529,"max_cost":13219.699441909319},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-4-argon-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"gemini-4-argon:batch","name":"Google: Gemini 4 Argon (batch)","created":1791907477,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":1.1e-6,"web_search":0.015400000000000002,"internal_reasoning":5.500000000000001e-6,"input_cache_read":5.5e-8,"input_cache_write":2.0625e-7,"max_prompt_cost":1.1534336,"max_completion_cost":5.190449000000001,"max_cost":5.305792800000001},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.001370357827212952,"web_search":19.18500958098133,"internal_reasoning":0.006851789136064761,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0002569420926024285,"max_prompt_cost":1436.9243290276484,"max_completion_cost":6466.156739908764,"max_cost":6609.8497209546595},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-4-argon-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"summarize","name":"ScaleDown: Summarize","created":1791893360,"description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4000000000000004e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.044000000000000004,"max_completion_cost":0.0,"max_cost":0.043824},"sats_pricing":{"prompt":0.000054814313088518084,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":54.814313088518084,"max_completion_cost":0.0,"max_cost":54.59505583616401},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":4000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"scaledown/summarize-20260928","alias_ids":null,"forwarded_model_id":null},{"id":"extract","name":"ScaleDown: Extract","created":1791893351,"description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4000000000000004e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.044000000000000004,"max_completion_cost":0.0,"max_cost":0.0044},"sats_pricing":{"prompt":0.000054814313088518084,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":54.814313088518084,"max_completion_cost":0.0,"max_cost":5.481431308851808},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":900000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"scaledown/extract-20260928","alias_ids":null,"forwarded_model_id":null},{"id":"muse-wonder","name":"Meta: Muse Wonder","created":1791807945,"description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":4.6137344,"max_completion_cost":20.761796000000004,"max_cost":21.223171200000003},"sats_pricing":{"prompt":0.005481431308851808,"completion":0.027407156544259043,"request":0.001,"image":0.0,"web_search":3.4258945680323802,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":5747.697316110593,"max_completion_cost":25864.626959635058,"max_cost":26439.398883818638},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-wonder-20261012","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"step-5-preview","name":"StepFun: Step 5 Preview","created":1791462849,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":2.9700000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":0.19008000000000003,"max_cost":1.21968},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.0036999661334749705,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":1370.357827212952,"max_completion_cost":236.7978325423981,"max_cost":1519.4527588137212},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"stepfun/step-5-preview-20261008","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.11,"max_completion_cost":0.0704,"max_cost":0.16632000000000002},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.000171294728401619,"max_prompt_cost":137.0357827212952,"max_completion_cost":87.70290094162893,"max_cost":207.19810347459835},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-haiku-5.5-20261007","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"claude-haiku-5.5:batch","name":"Anthropic: Claude Haiku 5.5 (batch)","created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":6.875e-8,"max_prompt_cost":0.055,"max_completion_cost":0.0352,"max_cost":0.08316000000000001},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.000342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":6.8517891360647605e-6,"input_cache_write":0.0000856473642008095,"max_prompt_cost":68.5178913606476,"max_completion_cost":43.85145047081446,"max_cost":103.59905173729918},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-haiku-5.5-20261007","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gemini-nano-banana-2.1","name":"Google: Nano Banana 2.1","created":1791300825,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"web_search":0.015400000000000002,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.1081344,"max_completion_cost":0.4866015,"max_cost":0.4974156},"sats_pricing":{"prompt":0.002055536740819428,"completion":0.010277683704097141,"request":0.001,"image":0.0,"web_search":19.18500958098133,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":134.71165584634204,"max_completion_cost":606.1983402350575,"max_cost":619.670328034388},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-nano-banana-2.1-20261006","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"}},{"id":"mistral-large-4-0","name":"Mistral: Mistral Large 4","created":1791294122,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":7.7e-7,"completion":2.31e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.700000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.80740352,"max_completion_cost":0.60555264,"max_cost":1.21110528},"sats_pricing":{"prompt":0.0009592504790490664,"completion":0.002877751437147199,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009592504790490665,"input_cache_write":0.0,"max_prompt_cost":1005.8470303193538,"max_completion_cost":754.3852727395154,"max_cost":1508.7705454790307},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large-4-0-20261006","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","none"],"default_effort":"high"}},{"id":"ling-3.1-flash","name":"inclusionAI: Ling 3.1 Flash","created":1790950024,"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":2.475e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.0825,"max_completion_cost":0.06488064,"max_cost":0.12575376},"sats_pricing":{"prompt":0.0001027768370409714,"completion":0.00030833051112291417,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000020555367408194277,"input_cache_write":0.0,"max_prompt_cost":102.7768370409714,"max_completion_cost":80.82699350780521,"max_cost":156.6614993795082},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.1-flash-20261002","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"gpt-6.1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2877.751437147199,"max_completion_cost":1754.0580188325787,"max_cost":4280.9978522132615},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-sol-pro-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-6.1-sol-pro:batch","name":"OpenAI: GPT-6.1 Sol Pro (batch)","created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0017129472840161902,"max_prompt_cost":1438.8757185735994,"max_completion_cost":877.0290094162893,"max_cost":2140.4989261066307},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-sol-pro-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2877.751437147199,"max_completion_cost":1754.0580188325787,"max_cost":4280.9978522132615},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-sol-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-6.1-sol:batch","name":"OpenAI: GPT-6.1 Sol (batch)","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0017129472840161902,"max_prompt_cost":1438.8757185735994,"max_completion_cost":877.0290094162893,"max_cost":2140.4989261066307},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-sol-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.2,"max_completion_cost":1.4080000000000001,"max_cost":3.3264000000000005},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2740.715654425904,"max_completion_cost":1754.0580188325787,"max_cost":4143.962069491967},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5.5-20260928","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"claude-sonnet-5.5:batch","name":"Anthropic: Claude Sonnet 5.5 (batch)","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.1,"max_completion_cost":0.7040000000000001,"max_cost":1.6632000000000002},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0017129472840161902,"max_prompt_cost":1370.357827212952,"max_completion_cost":877.0290094162893,"max_cost":2071.9810347459834},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5.5-20260928","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"perceptron-mk1.5","name":"Perceptron: Perceptron Mk1.5","created":1790352661,"description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","context_length":36864,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.006082560000000001,"max_completion_cost":0.0135168,"max_cost":0.018247680000000002},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.002055536740819428,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.57753064135674,"max_completion_cost":16.838956980792755,"max_cost":22.73259192407022},"per_request_limits":null,"top_provider":{"context_length":36864,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perceptron/perceptron-mk1.5-20260925","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"high"}},{"id":"ember-1","name":"Fireworks: Ember-1","created":1790208461,"description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":0.0,"max_prompt_cost":3.4603008,"max_completion_cost":15.571347000000001,"max_cost":15.9173784},"sats_pricing":{"prompt":0.004111073481638856,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0004111073481638856,"input_cache_write":0.0,"max_prompt_cost":4310.772987082945,"max_completion_cost":19398.47021972629,"max_cost":19829.549162863976},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"fireworks/ember-1-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"glm-5.3-prime","name":"Z.ai: GLM 5.3 Prime","created":1790199651,"description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.08e-6,"completion":9.68e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.160000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":3.08,"max_completion_cost":1.26877696,"max_cost":3.9450752},"sats_pricing":{"prompt":0.0038370019161962656,"completion":0.012059148879473977,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0007674003832392532,"input_cache_write":0.0,"max_prompt_cost":3837.0019161962655,"max_completion_cost":1580.616761930413,"max_cost":4914.695162967001},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-prime-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"qwen3.8-max-prime","name":"Qwen: Qwen3.8 Max Prime","created":1790191228,"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.0000132,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":4.4,"max_completion_cost":1.7301504,"max_cost":5.5534336},"sats_pricing":{"prompt":0.005481431308851808,"completion":0.016444293926555425,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":5481.431308851808,"max_completion_cost":2155.3864935414726,"max_cost":6918.355637879456},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-max-prime-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"}},{"id":"aion-3.5-mini","name":"AionLabs: Aion 3.5 Mini","created":1790170962,"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.7e-7,"completion":1.54e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.9800000000000003e-7,"input_cache_write":0.0,"max_prompt_cost":0.20185088,"max_completion_cost":0.05046272,"max_cost":0.22708224},"sats_pricing":{"prompt":0.0009592504790490664,"completion":0.0019185009580981328,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002466644088983314,"input_cache_write":0.0,"max_prompt_cost":251.46175757983846,"max_completion_cost":62.865439394959616,"max_cost":282.89447727731823},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.5-mini-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","high","low"],"default_effort":"high"}},{"id":"aion-3.5","name":"AionLabs: Aion 3.5","created":1790170961,"description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.8650752,"max_completion_cost":0.2162688,"max_cost":0.9732096000000001},"sats_pricing":{"prompt":0.004111073481638856,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.001027768370409714,"input_cache_write":0.0,"max_prompt_cost":1077.6932467707363,"max_completion_cost":269.4233116926841,"max_cost":1212.4049026170783},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.5-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","high","low"],"default_effort":"high"}},{"id":"solar-mini4","name":"Upstage: Solar Mini 4","created":1790160358,"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.02883584,"max_cost":0.05046272},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.8517891360647605e-6,"input_cache_write":0.0,"max_prompt_cost":35.92310822569121,"max_completion_cost":35.92310822569121,"max_cost":62.865439394959616},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"upstage/solar-mini4-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium"}},{"id":"command-a-plus","name":"Cohere: Command A+","created":1790102896,"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","context_length":192000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.06336,"max_completion_cost":0.1056,"max_cost":0.14784},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.002055536740819428,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":78.93261084746602,"max_completion_cost":131.5543514124434,"max_cost":184.17609197742073},"per_request_limits":null,"top_provider":{"context_length":192000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-a-plus-05-2026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.1155,"max_completion_cost":0.0704,"max_cost":0.17182000000000003},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.000171294728401619,"max_prompt_cost":143.88757185735994,"max_completion_cost":87.70290094162893,"max_cost":214.04989261066314},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-luna-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-6-luna-pro:batch","name":"OpenAI: GPT-6 Luna Pro (batch)","created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":6.875e-8,"max_prompt_cost":0.05775,"max_completion_cost":0.0352,"max_cost":0.08591000000000001},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.000342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":6.8517891360647605e-6,"input_cache_write":0.0000856473642008095,"max_prompt_cost":71.94378592867997,"max_completion_cost":43.85145047081446,"max_cost":107.02494630533157},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-luna-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-6-luna","name":"OpenAI: GPT-6 Luna","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.1155,"max_completion_cost":0.0704,"max_cost":0.17182000000000003},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.000171294728401619,"max_prompt_cost":143.88757185735994,"max_completion_cost":87.70290094162893,"max_cost":214.04989261066314},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-luna-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-6-luna:batch","name":"OpenAI: GPT-6 Luna (batch)","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":6.875e-8,"max_prompt_cost":0.05775,"max_completion_cost":0.0352,"max_cost":0.08591000000000001},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.000342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":6.8517891360647605e-6,"input_cache_write":0.0000856473642008095,"max_prompt_cost":71.94378592867997,"max_completion_cost":43.85145047081446,"max_cost":107.02494630533157},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-luna-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2877.751437147199,"max_completion_cost":1754.0580188325787,"max_cost":4280.9978522132615},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-sol-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-6-sol-pro:batch","name":"OpenAI: GPT-6 Sol Pro (batch)","created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0017129472840161902,"max_prompt_cost":1438.8757185735994,"max_completion_cost":877.0290094162893,"max_cost":2140.4989261066307},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-sol-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-6-sol","name":"OpenAI: GPT-6 Sol","created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2877.751437147199,"max_completion_cost":1754.0580188325787,"max_cost":4280.9978522132615},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-sol-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-6-sol:batch","name":"OpenAI: GPT-6 Sol (batch)","created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0017129472840161902,"max_prompt_cost":1438.8757185735994,"max_completion_cost":877.0290094162893,"max_cost":2140.4989261066307},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-sol-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.4,"max_completion_cost":2.8160000000000003,"max_cost":6.652800000000001},"sats_pricing":{"prompt":0.005481431308851808,"completion":0.027407156544259043,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.006851789136064761,"max_prompt_cost":5481.431308851808,"max_completion_cost":3508.1160376651574,"max_cost":8287.924138983934},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5.5-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"claude-opus-5.5:batch","name":"Anthropic: Claude Opus 5.5 (batch)","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.2,"max_completion_cost":1.4080000000000001,"max_cost":3.3264000000000005},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2740.715654425904,"max_completion_cost":1754.0580188325787,"max_cost":4143.962069491967},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5.5-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"mimo-v2.6-pro-ultraspeed","name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","created":1790021267,"description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","context_length":1048576,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.785e-6,"completion":9.57e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.9600000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":5.01743616,"max_completion_cost":1.25435904,"max_cost":5.644615679999999},"sats_pricing":{"prompt":0.005961056548376341,"completion":0.011922113096752682,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000049332881779666274,"input_cache_write":0.0,"max_prompt_cost":6250.62083127027,"max_completion_cost":1562.6552078175675,"max_cost":7031.9484351790525},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.6-pro-ultraspeed-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","created":1790021264,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5400000000000003e-7,"completion":3.0800000000000006e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.08e-9,"input_cache_write":0.0,"max_prompt_cost":0.16148070400000003,"max_completion_cost":0.04037017600000001,"max_cost":0.18166579200000002},"sats_pricing":{"prompt":0.0001918500958098133,"completion":0.0003837001916196266,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.837001916196266e-6,"input_cache_write":0.0,"max_prompt_cost":201.16940606387078,"max_completion_cost":50.292351515967695,"max_cost":226.31558182185464},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.6-flash-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","created":1790021259,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.785000000000001e-7,"completion":9.570000000000001e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.96e-9,"input_cache_write":0.0,"max_prompt_cost":0.5017436160000001,"max_completion_cost":0.12543590400000001,"max_cost":0.564461568},"sats_pricing":{"prompt":0.0005961056548376342,"completion":0.0011922113096752684,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.933288177966628e-6,"input_cache_write":0.0,"max_prompt_cost":625.0620831270271,"max_completion_cost":156.26552078175678,"max_cost":703.1948435179054},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.6-pro-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"grok-4.7","name":"SpaceXAI: Grok 4.7","created":1790007541,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":2.97,"max_cost":3.08},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":1370.357827212952,"max_completion_cost":3699.9661334749703,"max_cost":3837.0019161962655},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.7-20260916","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"}},{"id":"grok-4.7:batch","name":"SpaceXAI: Grok 4.7 (batch)","created":1790007541,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.76e-6,"completion":5.28e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":0.0,"max_prompt_cost":0.88,"max_completion_cost":2.3760000000000003,"max_cost":2.4640000000000004},"sats_pricing":{"prompt":0.002192572523540723,"completion":0.00657771757062217,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0005481431308851808,"input_cache_write":0.0,"max_prompt_cost":1096.2862617703615,"max_completion_cost":2959.9729067799767,"max_cost":3069.6015329570128},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.7-20260916","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"}},{"id":"qwen3.8-omni-flash","name":"Qwen: Qwen3.8 Omni Flash","created":1789959954,"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","context_length":1000000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","audio","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.170000000000001e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7600000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.165,"max_completion_cost":0.06776422400000001,"max_cost":0.21113734400000003},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0006440681787900875,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002192572523540723,"input_cache_write":0.0,"max_prompt_cost":205.5536740819428,"max_completion_cost":84.41930433037435,"max_cost":263.03064724304875},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-omni-flash-20260918","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}},{"id":"ternary-bonsai-2-27b","name":"PrismML: Ternary Bonsai 2 27B","created":1789754046,"description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.0180224,"max_cost":0.03694592},"sats_pricing":{"prompt":0.0001027768370409714,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000513884185204857,"input_cache_write":0.0,"max_prompt_cost":26.942331169268407,"max_completion_cost":22.451942641057006,"max_cost":46.02648241416686},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"prism-ml/ternary-bonsai-2-27b-20260918","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","medium","none"],"default_effort":"xhigh"}},{"id":"glm-5.3-flashx","name":"Z.ai: GLM 5.3 FlashX","created":1789744020,"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.0700000000000003e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.42677043200000003,"max_completion_cost":0.18022400000000002,"max_cost":0.5536481280000001},"sats_pricing":{"prompt":0.0005070323960687923,"completion":0.0017129472840161902,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001027768370409714,"input_cache_write":0.0,"max_prompt_cost":531.6620017402299,"max_completion_cost":224.51942641057008,"max_cost":689.7236779332712},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flashx-20260918","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"deepseek-pro-latest","name":"DeepSeek: DeepSeek Pro Latest","created":1789399174,"description":"This model always redirects to the latest model in the DeepSeek Pro family.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.0197e-7,"completion":8.8e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.0197e-7,"input_cache_write":0.0,"max_prompt_cost":0.10692329472,"max_completion_cost":3.4603008,"max_cost":3.5271278592},"sats_pricing":{"prompt":0.00012703217058264064,"completion":0.010962862617703616,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00012703217058264064,"input_cache_write":0.0,"max_prompt_cost":133.202885300863,"max_completion_cost":4310.772987082945,"max_cost":4394.024790395984},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~deepseek/deepseek-pro-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"deepseek-flash-latest","name":"DeepSeek: DeepSeek Flash Latest","created":1789399150,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":6.6e-9,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":0.0,"max_prompt_cost":0.0069206016,"max_completion_cost":0.5190449,"max_cost":0.5197369628},"sats_pricing":{"prompt":8.222146963277712e-6,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.8517891360647605e-6,"input_cache_write":0.0,"max_prompt_cost":8.62154597416589,"max_completion_cost":646.6156739908763,"max_cost":647.4778318771517},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~deepseek/deepseek-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"schematron-v2-turbo","name":"Inference.net: Schematron V2 Turbo","created":1789176949,"description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-8,"completion":1.65e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.0042239999999999995,"max_completion_cost":0.00135168,"max_cost":0.005305344},"sats_pricing":{"prompt":0.000041110734816388555,"completion":0.0002055536740819428,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":5.262174056497734,"max_completion_cost":1.6838956980792754,"max_cost":6.609290614961155},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inference-net/schematron-v2-turbo-20260902","alias_ids":null,"forwarded_model_id":null},{"id":"schematron-v2-small","name":"Inference.net: Schematron V2 Small","created":1789176933,"description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.53e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.00704,"max_completion_cost":0.002072576,"max_cost":0.008662016},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.00031518230025897893,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0,"max_prompt_cost":8.770290094162892,"max_completion_cost":2.5819734037215554,"max_cost":10.790964931858023},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inference-net/schematron-v2-small-20260902","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-astra-latest","name":"OpenAI: GPT Astra Latest","created":1789130932,"description":"This model always redirects to the latest model in the GPT Astra family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.55,"max_completion_cost":7.040000000000001,"max_cost":17.182000000000002},"sats_pricing":{"prompt":0.013703578272129521,"completion":0.0685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.001370357827212952,"input_cache_write":0.0171294728401619,"max_prompt_cost":14388.757185735996,"max_completion_cost":8770.290094162894,"max_cost":21404.989261066312},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-astra-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-sol-latest","name":"OpenAI: GPT Sol Latest","created":1789130928,"description":"This model always redirects to the latest model in the GPT Sol family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2877.751437147199,"max_completion_cost":1754.0580188325787,"max_cost":4280.9978522132615},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-sol-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-terra-latest","name":"OpenAI: GPT Terra Latest","created":1789130925,"description":"This model always redirects to the latest model in the GPT Terra family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0017129472840161902,"max_prompt_cost":1438.8757185735994,"max_completion_cost":877.0290094162893,"max_cost":2140.4989261066307},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-terra-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-luna-latest","name":"OpenAI: GPT Luna Latest","created":1789130922,"description":"This model always redirects to the latest model in the GPT Luna family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.1155,"max_completion_cost":0.0704,"max_cost":0.17182000000000003},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.000171294728401619,"max_prompt_cost":143.88757185735994,"max_completion_cost":87.70290094162893,"max_cost":214.04989261066314},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-luna-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"fugu-ultra-v2","name":"Sakana: Fugu Ultra v2","created":1789105383,"description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000033,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":5.500000000000001,"max_completion_cost":4.224,"max_cost":9.02},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.041110734816388564,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":6851.789136064761,"max_completion_cost":5262.174056497735,"max_cost":11236.934183146204},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/fugu-ultra-v2-20260911","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"xhigh"}},{"id":"fugu-max","name":"Sakana: Fugu Max","created":1789104771,"description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.2,"max_completion_cost":0.8448,"max_cost":2.7632000000000003},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":2740.715654425904,"max_completion_cost":1052.4348112995472,"max_cost":3442.3388619589355},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/fugu-max-20260911","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"high"}},{"id":"ling-3.0-flash-vl","name":"inclusionAI: Ling 3.0 Flash VL","created":1789056114,"description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","context_length":131072,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":1.9800000000000003e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.32e-8,"input_cache_write":0.0,"max_prompt_cost":0.008650752,"max_completion_cost":0.006488064000000001,"max_cost":0.012976128},"sats_pricing":{"prompt":0.00008222146963277711,"completion":0.0002466644088983314,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000016444293926555425,"input_cache_write":0.0,"max_prompt_cost":10.776932467707361,"max_completion_cost":8.082699350780523,"max_cost":16.165398701561042},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.0-flash-vl-20260910","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":4.9500000000000006e-8,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.9800000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.05190451200000001,"max_completion_cost":0.5190449,"max_cost":0.5242353710000001},"sats_pricing":{"prompt":0.00006166610222458285,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000024666440889833137,"input_cache_write":0.0,"max_prompt_cost":64.66159480624418,"max_completion_cost":646.6156739908763,"max_cost":653.0818581379417},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"deepseek-v4.1-flash:batch","name":"DeepSeek: DeepSeek V4.1 Flash (batch)","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.2320000000000002e-7,"completion":3.6960000000000003e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.6960000000000005e-9,"input_cache_write":0.0,"max_prompt_cost":0.12918456320000002,"max_completion_cost":0.048444211200000004,"max_cost":0.16148070400000003},"sats_pricing":{"prompt":0.00015348007664785064,"completion":0.0004604402299435519,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.604402299435519e-6,"input_cache_write":0.0,"max_prompt_cost":160.93552485109663,"max_completion_cost":60.35082181916123,"max_cost":201.16940606387078},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"mercury-2.5","name":"Inception: Mercury 2.5","created":1788892137,"description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...","context_length":260000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4000000000000004e-8,"completion":1.65e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000005e-9,"input_cache_write":0.0,"max_prompt_cost":0.01144,"max_completion_cost":0.01081344,"max_cost":0.019369856},"sats_pricing":{"prompt":0.000054814313088518084,"completion":0.0002055536740819428,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.481431308851808e-6,"input_cache_write":0.0,"max_prompt_cost":14.2517214030147,"max_completion_cost":13.471165584634203,"max_cost":24.130576165079784},"per_request_limits":null,"top_provider":{"context_length":260000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inception/mercury-2.5-20260908","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"}},{"id":"nex-n2.5-mini","name":"Nex AGI: Nex-N2.5-Mini","created":1788890061,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.75e-8,"completion":1.1e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.7500000000000002e-9,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.02595219,"max_cost":0.0266731025},"sats_pricing":{"prompt":0.0000342589456803238,"completion":0.0001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.4258945680323803e-6,"input_cache_write":0.0,"max_prompt_cost":8.980777056422802,"max_completion_cost":32.33071518165245,"max_cost":33.228813442662144},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nex-agi/nex-n2.5-mini-20260908","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","none"],"default_effort":"high"}},{"id":"nex-n2.5-pro","name":"Nex AGI: Nex-N2.5-Pro","created":1788890050,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.064880475,"max_cost":0.0670432125},"sats_pricing":{"prompt":0.0001027768370409714,"completion":0.000342589456803238,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000020555367408194277,"input_cache_write":0.0,"max_prompt_cost":26.942331169268407,"max_completion_cost":80.82678795413113,"max_cost":83.5210827371602},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nex-agi/nex-n2.5-pro-20260907","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","none"],"default_effort":"high"}},{"id":"gpt-6-astra","name":"OpenAI: GPT-6 Astra","created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.55,"max_completion_cost":7.040000000000001,"max_cost":17.182000000000002},"sats_pricing":{"prompt":0.013703578272129521,"completion":0.0685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.001370357827212952,"input_cache_write":0.0171294728401619,"max_prompt_cost":14388.757185735996,"max_completion_cost":8770.290094162894,"max_cost":21404.989261066312},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-astra-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-6-astra:batch","name":"OpenAI: GPT-6 Astra (batch)","created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.775,"max_completion_cost":3.5200000000000005,"max_cost":8.591000000000001},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.0342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.00856473642008095,"max_prompt_cost":7194.378592867998,"max_completion_cost":4385.145047081447,"max_cost":10702.494630533156},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-astra-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro","created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.55,"max_completion_cost":7.040000000000001,"max_cost":17.182000000000002},"sats_pricing":{"prompt":0.013703578272129521,"completion":0.0685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.001370357827212952,"input_cache_write":0.0171294728401619,"max_prompt_cost":14388.757185735996,"max_completion_cost":8770.290094162894,"max_cost":21404.989261066312},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-astra-pro-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"gpt-6-astra-pro:batch","name":"OpenAI: GPT-6 Astra Pro (batch)","created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.775,"max_completion_cost":3.5200000000000005,"max_cost":8.591000000000001},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.0342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.00856473642008095,"max_prompt_cost":7194.378592867998,"max_completion_cost":4385.145047081447,"max_cost":10702.494630533156},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-astra-pro-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"qwen3.8-max-0902","name":"Qwen: Qwen3.8 Max (0902)","created":1788469704,"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.2,"max_completion_cost":0.8650752,"max_cost":2.7767168},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":2740.715654425904,"max_completion_cost":1077.6932467707363,"max_cost":3459.177818939728},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-max-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"}},{"id":"muse-spark-1.3-contributor","name":"Meta: Muse Spark 1.3 Contributor","created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":2.2000000000000003e-9,"input_cache_write":0.0,"max_prompt_cost":0.11534336,"max_completion_cost":0.20761796000000002,"max_cost":0.21915234000000003},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":3.4258945680323802,"internal_reasoning":0.0,"input_cache_read":2.740715654425904e-6,"input_cache_write":0.0,"max_prompt_cost":143.69243290276484,"max_completion_cost":258.6462695963505,"max_cost":273.0155677009401},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.3-contributor-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"muse-spark-1.3","name":"Meta: Muse Spark 1.3","created":1788378359,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":4.675e-6,"request":0.0,"image":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":1.4417920000000002,"max_completion_cost":4.41188165,"max_cost":4.5560614},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.0058240207656550455,"request":0.001,"image":0.0,"web_search":3.4258945680323802,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":1796.1554112845606,"max_completion_cost":5496.233228922448,"max_cost":5675.849455229818},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.3-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gemini-3.8-flash","name":"Google: Gemini 3.8 Flash","created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":9.075000000000001e-7,"completion":4.537500000000001e-6,"request":0.0,"image":9.075000000000001e-7,"web_search":0.015400000000000002,"internal_reasoning":4.537500000000001e-6,"input_cache_read":9.075000000000002e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.9515827200000001,"max_completion_cost":0.29736960000000007,"max_cost":1.1894784000000003},"sats_pricing":{"prompt":0.0011305452074506855,"completion":0.005652726037253428,"request":0.001,"image":0.0011305452074506855,"web_search":19.18500958098133,"internal_reasoning":0.005652726037253428,"input_cache_read":0.00011305452074506855,"input_cache_write":0.00005709824280053971,"max_prompt_cost":1185.46257144781,"max_completion_cost":370.45705357744066,"max_cost":1481.8282143097626},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.8-flash-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"gemini-3.8-flash:batch","name":"Google: Gemini 3.8 Flash (batch)","created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":2.0625e-6,"request":0.0,"image":4.125e-7,"web_search":0.015400000000000002,"internal_reasoning":2.0625e-6,"input_cache_read":4.125e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.4325376,"max_completion_cost":0.135168,"max_cost":0.540672},"sats_pricing":{"prompt":0.000513884185204857,"completion":0.0025694209260242852,"request":0.001,"image":0.000513884185204857,"web_search":19.18500958098133,"internal_reasoning":0.0025694209260242852,"input_cache_read":0.0000513884185204857,"input_cache_write":0.00005709824280053971,"max_prompt_cost":538.8466233853682,"max_completion_cost":168.38956980792756,"max_cost":673.5582792317102},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.8-flash-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.000000000000002,"max_completion_cost":7.040000000000001,"max_cost":16.632},"sats_pricing":{"prompt":0.013703578272129521,"completion":0.0685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0171294728401619,"max_prompt_cost":13703.578272129522,"max_completion_cost":8770.290094162894,"max_cost":20719.810347459836},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-fable-5.1-20260831","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"claude-fable-5.1:batch","name":"Anthropic: Claude Fable 5.1 (batch)","created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.0342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000171294728401619,"input_cache_write":0.00856473642008095,"max_prompt_cost":6851.789136064761,"max_completion_cost":4385.145047081447,"max_cost":10359.905173729918},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-fable-5.1-20260831","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"granite-4.2-8b","name":"IBM: Granite 4.2 8B","created":1788206780,"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.008650752,"max_completion_cost":0.0324401,"max_cost":0.033305228},"sats_pricing":{"prompt":0.00008222146963277711,"completion":0.000342589456803238,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000020555367408194277,"input_cache_write":0.0,"max_prompt_cost":10.776932467707361,"max_completion_cost":40.413222682337164,"max_cost":41.490981706283605},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"ibm-granite/granite-4.2-8b-20260831","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"hy4-preview","name":"Tencent: Hy4 preview","created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9.174e-7,"completion":2.7511000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.6200000000000003e-8,"input_cache_write":0.0,"max_prompt_cost":0.9619636224,"max_completion_cost":0.17607040000000002,"max_cost":1.0793204224},"sats_pricing":{"prompt":0.001142878427895602,"completion":0.003427264925859593,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000057555028742943986,"input_cache_write":0.0,"max_prompt_cost":1198.3948904090587,"max_completion_cost":219.34495525501396,"max_cost":1344.595626278754},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":64000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy4-preview-20260827","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"glm-flash-latest","name":"Z.ai: GLM Flash Latest","created":1787817633,"description":"This model always redirects to the latest model in the GLM Flash family.","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":3.1350000000000006e-8,"completion":1.0153000000000001e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.1350000000000006e-8,"input_cache_write":0.0,"max_prompt_cost":0.032872857600000006,"max_completion_cost":0.013307740160000001,"max_cost":0.04207149056000001},"sats_pricing":{"prompt":0.000039055198075569135,"completion":0.00012648402745175547,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000039055198075569135,"input_cache_write":0.0,"max_prompt_cost":40.95234337728798,"max_completion_cost":16.578514446156493,"max_cost":52.41181490128348},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~z-ai/glm-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"qwen3.8-flash","name":"Qwen: Qwen3.8 Flash","created":1787773060,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.170000000000001e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7600000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.165,"max_completion_cost":0.06776422400000001,"max_cost":0.21113734400000003},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0006440681787900875,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002192572523540723,"input_cache_write":0.0,"max_prompt_cost":205.5536740819428,"max_completion_cost":84.41930433037435,"max_cost":263.03064724304875},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-flash-20260826","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}},{"id":"glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.173014875,"max_completion_cost":0.51904435,"max_cost":0.53634592},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":215.53844380047317,"max_completion_cost":646.6149888119627,"max_cost":668.1689359688471},"per_request_limits":null,"top_provider":{"context_length":1048575,"max_completion_tokens":943717,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flash-20260826","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"glm-5.3-flash:batch","name":"Z.ai: GLM 5.3 Flash (batch)","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":1.9800000000000003e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.025952256000000003,"max_cost":0.07641497600000001},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.0002466644088983314,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.0,"max_prompt_cost":71.84621645138242,"max_completion_cost":32.33079740312209,"max_cost":95.19623679808171},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flash-20260826","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"muse-spark-1.2-contributor","name":"Meta: Muse Spark 1.2 Contributor","created":1787336476,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":2.2000000000000003e-9,"input_cache_write":0.0,"max_prompt_cost":0.11534336,"max_completion_cost":0.20761796000000002,"max_cost":0.21915234000000003},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":3.4258945680323802,"internal_reasoning":0.0,"input_cache_read":2.740715654425904e-6,"input_cache_write":0.0,"max_prompt_cost":143.69243290276484,"max_completion_cost":258.6462695963505,"max_cost":273.0155677009401},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.2-contributor-20260805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"deepseek-v4-flash-vision-exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","created":1787311563,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":2.3716000000000001e-7,"completion":7.114800000000001e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.546e-9,"input_cache_write":0.0,"max_prompt_cost":0.24868028416000001,"max_completion_cost":0.18651021312000002,"max_cost":0.37302042624000004},"sats_pricing":{"prompt":0.0002954491475471124,"completion":0.0008863474426413374,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.40065469468085e-6,"input_cache_write":0.0,"max_prompt_cost":309.80088533836096,"max_completion_cost":232.35066400377076,"max_cost":464.7013280075415},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-flash-vision-exp-20260821","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"hy-mt2-1.8b","name":"Tencent: Hy-MT2-1.8B","created":1787231581,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.84e-8,"completion":1.9470000000000002e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0003964928,"max_completion_cost":0.0007974912000000001,"max_cost":0.0009957376},"sats_pricing":{"prompt":0.00006029574439736989,"completion":0.0002425533354166925,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.4939427381032541,"max_completion_cost":0.9934984618667725,"max_cost":1.2404698309183995},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy-mt2-1.8b-20260521","alias_ids":null,"forwarded_model_id":null},{"id":"hy-mt2-30b-a3b","name":"Tencent: Hy-MT2-30B-A3B","created":1787231561,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.14e-8,"completion":3.2450000000000003e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0006668288,"max_completion_cost":0.0013291520000000001,"max_cost":0.0016625664},"sats_pricing":{"prompt":0.00010140647921375845,"completion":0.00040425555902782085,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.8307218777191092,"max_completion_cost":1.6558307697779542,"max_cost":2.0711917086375085},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy-mt2-30b-a3b-20260521","alias_ids":null,"forwarded_model_id":null},{"id":"glm-latest","name":"Z.ai: GLM Latest","created":1787151053,"description":"This model always redirects to the latest GLM model from Z.ai.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":7.689000000000001e-8,"completion":1.54e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.579e-8,"input_cache_write":0.0,"max_prompt_cost":0.08062500864000001,"max_completion_cost":1.45332572,"max_cost":1.46138825162},"sats_pricing":{"prompt":0.00009578801212218535,"completion":0.0019185009580981328,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000944176542949724,"input_cache_write":0.0,"max_prompt_cost":100.44101059903262,"max_completion_cost":1810.5238871744536,"max_cost":1820.5680265495619},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~z-ai/glm-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"hy-mt2-7b","name":"Tencent: Hy-MT2-7B","created":1787148797,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.14e-8,"completion":3.2450000000000003e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0006668288,"max_completion_cost":0.0013291520000000001,"max_cost":0.0016625664},"sats_pricing":{"prompt":0.00010140647921375845,"completion":0.00040425555902782085,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.8307218777191092,"max_completion_cost":1.6558307697779542,"max_cost":2.0711917086375085},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy-mt2-7b-20260521","alias_ids":null,"forwarded_model_id":null},{"id":"glm-5.3","name":"Z.ai: GLM 5.3","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.689000000000001e-8,"completion":1.54e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.579e-8,"input_cache_write":0.0,"max_prompt_cost":0.08062500864000001,"max_completion_cost":1.45332572,"max_cost":1.46138825162},"sats_pricing":{"prompt":0.00009578801212218535,"completion":0.0019185009580981328,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000944176542949724,"input_cache_write":0.0,"max_prompt_cost":100.44101059903262,"max_completion_cost":1810.5238871744536,"max_cost":1820.5680265495619},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-20260816","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"glm-5.3:batch","name":"Z.ai: GLM 5.3 (batch)","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.95e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.51904512,"max_completion_cost":0.2883584,"max_cost":0.7425228800000001},"sats_pricing":{"prompt":0.0006166610222458283,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":646.6159480624417,"max_completion_cost":359.2310822569121,"max_cost":925.0200368115487},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-20260816","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"qwen3.8-27b","name":"Qwen: Qwen3.8 27B","created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","context_length":1024000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":2.0625e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.48660356250000003,"max_cost":0.49092903750000005},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0025694209260242852,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000513884185204857,"input_cache_write":0.0,"max_prompt_cost":53.88466233853681,"max_completion_cost":606.2009096559835,"max_cost":611.5894992220417},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-27b-20260814","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","medium","low","none"],"default_effort":"xhigh"}},{"id":"gemini-3.7-flash","name":"Google: Gemini 3.7 Flash","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.125e-6,"request":0.0,"image":8.25e-7,"web_search":0.015400000000000002,"internal_reasoning":4.125e-6,"input_cache_read":8.25e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.8650752,"max_completion_cost":0.270336,"max_cost":1.081344},"sats_pricing":{"prompt":0.001027768370409714,"completion":0.0051388418520485705,"request":0.001,"image":0.001027768370409714,"web_search":19.18500958098133,"internal_reasoning":0.0051388418520485705,"input_cache_read":0.0001027768370409714,"input_cache_write":0.00005709824280053971,"max_prompt_cost":1077.6932467707363,"max_completion_cost":336.7791396158551,"max_cost":1347.1165584634205},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.7-flash-20260813","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"gemini-3.7-flash:batch","name":"Google: Gemini 3.7 Flash (batch)","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":2.0625e-6,"request":0.0,"image":4.125e-7,"web_search":0.015400000000000002,"internal_reasoning":2.0625e-6,"input_cache_read":4.125e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.4325376,"max_completion_cost":0.135168,"max_cost":0.540672},"sats_pricing":{"prompt":0.000513884185204857,"completion":0.0025694209260242852,"request":0.001,"image":0.000513884185204857,"web_search":19.18500958098133,"internal_reasoning":0.0025694209260242852,"input_cache_read":0.0000513884185204857,"input_cache_write":0.00005709824280053971,"max_prompt_cost":538.8466233853682,"max_completion_cost":168.38956980792756,"max_cost":673.5582792317102},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.7-flash-20260813","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"seed-2-1-turbo","name":"ByteDance Seed: Seed 2.1 Turbo","created":1786552176,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.64880475,"max_cost":0.663223},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":179.61554112845604,"max_completion_cost":808.2678795413113,"max_cost":826.2298447615051},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2-1-turbo-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","created":1786551702,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.3068672,"max_completion_cost":0.8650752,"max_cost":2.8835840000000004},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":2873.8486580552967,"max_completion_cost":1077.6932467707363,"max_cost":3592.3108225691212},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-2.4t-a95b-20260812","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","medium","low"],"default_effort":"xhigh"}},{"id":"seed-2.0-code","name":"ByteDance Seed: Seed-2.0-Code","created":1786550701,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.4325376,"max_cost":0.5046272},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":179.61554112845604,"max_completion_cost":538.8466233853682,"max_cost":628.6543939495962},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2.0-code-20260730","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","created":1786549364,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.133e-7,"completion":4.5209999999999996e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.0780000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":0.1188036608,"max_completion_cost":4.266549078,"max_cost":4.2784294894},"sats_pricing":{"prompt":0.00014114685620293405,"completion":0.005632170669845232,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001342950670668693,"input_cache_write":0.0,"max_prompt_cost":148.00320588984778,"max_completion_cost":5315.180840205003,"max_cost":5329.98121725273},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-pro-20260813","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"grok-4.6","name":"SpaceXAI: Grok 4.6","created":1786548957,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":2.97,"max_cost":3.08},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":1370.357827212952,"max_completion_cost":3699.9661334749703,"max_cost":3837.0019161962655},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.6-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"}},{"id":"grok-4.6:batch","name":"SpaceXAI: Grok 4.6 (batch)","created":1786548957,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.76e-6,"completion":5.28e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":0.0,"max_prompt_cost":0.88,"max_completion_cost":2.3760000000000003,"max_cost":2.4640000000000004},"sats_pricing":{"prompt":0.002192572523540723,"completion":0.00657771757062217,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0005481431308851808,"input_cache_write":0.0,"max_prompt_cost":1096.2862617703615,"max_completion_cost":2959.9729067799767,"max_cost":3069.6015329570128},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.6-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"}},{"id":"lfm-2.5-2.6b","name":"LiquidAI: LFM2.5-2.6B","created":1786470519,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.85e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.049280000000000004,"max_completion_cost":0.0045056,"max_cost":0.05063168},"sats_pricing":{"prompt":0.0004796252395245332,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000054814313088518084,"input_cache_write":0.0,"max_prompt_cost":61.392030659140254,"max_completion_cost":5.612985660264251,"max_cost":63.07592635721952},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"liquid/lfm-2.5-2.6b-20260811","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.700000000000001e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.020185088000000004,"max_completion_cost":0.05190438,"max_cost":0.053922935},"sats_pricing":{"prompt":0.00009592504790490665,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000054814313088518084,"input_cache_write":0.0,"max_prompt_cost":25.146175757983848,"max_completion_cost":64.6614303633049,"max_cost":67.17610549413203},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"sakana-namazu","name":"Sakana: Sakana Namazu","created":1786410129,"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.0450000000000002e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"web_search":0.007700000000000001,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.27394048000000004,"max_completion_cost":0.2883584,"max_cost":0.49381376000000005},"sats_pricing":{"prompt":0.0013018399358523045,"completion":0.005481431308851808,"request":0.001,"image":0.0,"web_search":9.592504790490665,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":341.2695281440665,"max_completion_cost":359.2310822569121,"max_cost":615.183228364962},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/namazu-20260811","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","none"],"default_effort":"high"}},{"id":"solar-pro4","name":"Upstage: Solar Pro 4","created":1786371636,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.08650752,"max_completion_cost":0.08650752,"max_cost":0.15138816},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":107.76932467707363,"max_completion_cost":107.76932467707363,"max_cost":188.59631818487884},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"upstage/solar-pro4-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium"}},{"id":"muse-glimmer-30b","name":"Meta: Muse Glimmer 30B","created":1786302394,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.02162688,"max_cost":0.05947392},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000054814313088518084,"input_cache_write":0.0,"max_prompt_cost":53.88466233853681,"max_completion_cost":26.942331169268407,"max_cost":74.09141071548811},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-glimmer-30b-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"ling-3.0-tiny","name":"inclusionAI: Ling 3.0 Tiny","created":1786034890,"description":"Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-8,"completion":4.9500000000000006e-8,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-9,"input_cache_write":0.0,"max_prompt_cost":0.004325376,"max_completion_cost":0.012375000000000002,"max_cost":0.012575376000000003},"sats_pricing":{"prompt":0.000020555367408194277,"completion":0.00006166610222458285,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.111073481638856e-6,"input_cache_write":0.0,"max_prompt_cost":5.388466233853681,"max_completion_cost":15.416525556145713,"max_cost":15.666149937950824},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":250000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.0-tiny-20260806","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"muse-spark-1.2","name":"Meta: Muse Spark 1.2","created":1785959287,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":4.675e-6,"request":0.0,"image":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":1.4417920000000002,"max_completion_cost":4.41188165,"max_cost":4.5560614},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.0058240207656550455,"request":0.001,"image":0.0,"web_search":3.4258945680323802,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":1796.1554112845606,"max_completion_cost":5496.233228922448,"max_cost":5675.849455229818},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.2-20260805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"deepseek-v4-flash-latest","name":"DeepSeek: DeepSeek V4 Flash Latest","created":1785606009,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":6.49e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.850000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.0680525824,"max_completion_cost":0.31142694000000004,"max_cost":0.3182322242},"sats_pricing":{"prompt":0.00008085111180556417,"completion":0.0004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004796252395245332,"input_cache_write":0.0,"max_prompt_cost":84.77853541263126,"max_completion_cost":387.96940439452584,"max_cost":396.4472902762336},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~deepseek/deepseek-v4-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":6.49e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.850000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.0680525824,"max_completion_cost":0.31142694000000004,"max_cost":0.3182322242},"sats_pricing":{"prompt":0.00008085111180556417,"completion":0.0004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004796252395245332,"input_cache_write":0.0,"max_prompt_cost":84.77853541263126,"max_completion_cost":387.96940439452584,"max_cost":396.4472902762336},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-flash-20260731","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"inkling-small","name":"Thinking Machines: Inkling Small","created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","context_length":524288,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.95e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.25952256,"max_completion_cost":0.34603008,"max_cost":0.47579136},"sats_pricing":{"prompt":0.0006166610222458283,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":323.30797403122085,"max_completion_cost":431.0772987082945,"max_cost":592.7312857239049},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thinkingmachines/inkling-small-20260730","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"}},{"id":"qwen3.7-flash","name":"Qwen: Qwen3.7 Flash","created":1785190561,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":3.3e-8,"completion":1.4300000000000002e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-9,"input_cache_write":4.1800000000000004e-8,"max_prompt_cost":0.032999999999999995,"max_completion_cost":0.009371648000000002,"max_cost":0.04020896},"sats_pricing":{"prompt":0.000041110734816388555,"completion":0.00017814651753768378,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.222146963277712e-6,"input_cache_write":0.000052073597434092175,"max_prompt_cost":41.11073481638855,"max_completion_cost":11.675010173349644,"max_cost":50.09151187281136},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-flash-20260727","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}},{"id":"claude-opus-5","name":"Anthropic: Claude Opus 5","created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.0342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.00856473642008095,"max_prompt_cost":6851.789136064761,"max_completion_cost":4385.145047081447,"max_cost":10359.905173729918},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5-20260723","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"claude-opus-5:batch","name":"Anthropic: Claude Opus 5 (batch)","created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":2.7500000000000004,"max_completion_cost":1.7600000000000002,"max_cost":4.158},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.0171294728401619,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.004282368210040475,"max_prompt_cost":3425.8945680323804,"max_completion_cost":2192.5725235407235,"max_cost":5179.952586864959},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5-20260723","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"ling-3.0-flash","name":"inclusionAI: Ling 3.0 Flash","created":1784818580,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.3100000000000002e-8,"completion":6.93e-8,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.620000000000001e-9,"input_cache_write":0.0,"max_prompt_cost":0.0060555264000000004,"max_completion_cost":0.0022708224,"max_cost":0.007569408000000001},"sats_pricing":{"prompt":0.000028777514371471993,"completion":0.00008633254311441598,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.755502874294399e-6,"input_cache_write":0.0,"max_prompt_cost":7.543852727395154,"max_completion_cost":2.8289447727731827,"max_cost":9.429815909243944},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.0-flash-20260723","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"gemini-3.6-flash","name":"Google: Gemini 3.6 Flash","created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.125e-6,"request":0.0,"image":8.25e-7,"web_search":0.015400000000000002,"internal_reasoning":4.125e-6,"input_cache_read":8.25e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.8650752,"max_completion_cost":0.270336,"max_cost":1.081344},"sats_pricing":{"prompt":0.001027768370409714,"completion":0.0051388418520485705,"request":0.001,"image":0.001027768370409714,"web_search":19.18500958098133,"internal_reasoning":0.0051388418520485705,"input_cache_read":0.0001027768370409714,"input_cache_write":0.00005709824280053971,"max_prompt_cost":1077.6932467707363,"max_completion_cost":336.7791396158551,"max_cost":1347.1165584634205},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.6-flash-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gemini-3.6-flash:batch","name":"Google: Gemini 3.6 Flash (batch)","created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":2.0625e-6,"request":0.0,"image":4.125e-7,"web_search":0.015400000000000002,"internal_reasoning":2.0625e-6,"input_cache_read":4.125e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.4325376,"max_completion_cost":0.135168,"max_cost":0.540672},"sats_pricing":{"prompt":0.000513884185204857,"completion":0.0025694209260242852,"request":0.001,"image":0.000513884185204857,"web_search":19.18500958098133,"internal_reasoning":0.0025694209260242852,"input_cache_read":0.0000513884185204857,"input_cache_write":0.00005709824280053971,"max_prompt_cost":538.8466233853682,"max_completion_cost":168.38956980792756,"max_cost":673.5582792317102},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.6-flash-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gemini-3.5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":3.3e-7,"web_search":0.015400000000000002,"internal_reasoning":2.7500000000000004e-6,"input_cache_read":3.3e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.34603008,"max_completion_cost":0.18022400000000002,"max_cost":0.5046272},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0034258945680323803,"request":0.001,"image":0.0004111073481638856,"web_search":19.18500958098133,"internal_reasoning":0.0034258945680323803,"input_cache_read":0.000041110734816388555,"input_cache_write":0.00011419648560107929,"max_prompt_cost":431.0772987082945,"max_completion_cost":224.51942641057008,"max_cost":628.6543939495962},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-lite-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"}},{"id":"gemini-3.5-flash-lite:batch","name":"Google: Gemini 3.5 Flash Lite (batch)","created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":1.65e-7,"web_search":0.015400000000000002,"internal_reasoning":1.3750000000000002e-6,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.09011200000000001,"max_cost":0.2523136},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0017129472840161902,"request":0.001,"image":0.0002055536740819428,"web_search":19.18500958098133,"internal_reasoning":0.0017129472840161902,"input_cache_read":0.000020555367408194277,"input_cache_write":0.0,"max_prompt_cost":215.53864935414725,"max_completion_cost":112.25971320528504,"max_cost":314.3271969747981},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-lite-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"}},{"id":"longcat-2.0","name":"Meituan: LongCat 2.0","created":1784554658,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","context_length":1048756,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-9,"input_cache_write":0.0,"max_prompt_cost":0.34608948,"max_completion_cost":0.34603008,"max_cost":0.60561204},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.222146963277712e-6,"input_cache_write":0.0,"max_prompt_cost":431.15129803096397,"max_completion_cost":431.0772987082945,"max_cost":754.4592720621848},"per_request_limits":null,"top_provider":{"context_length":1048756,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meituan/longcat-2.0-20260720","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true}},{"id":"inkling","name":"Thinking Machines: Inkling","created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","context_length":524288,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":4.4550000000000005e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.87e-7,"input_cache_write":0.0,"max_prompt_cost":0.5767168,"max_completion_cost":2.102131845,"max_cost":2.159803745},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.005549949200212456,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00023296083062620182,"input_cache_write":0.0,"max_prompt_cost":718.4621645138242,"max_completion_cost":2618.7934796630493,"max_cost":2690.639970185997},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":471859,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thinkingmachines/inkling-20260715","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"}},{"id":"kimi-k3","name":"MoonshotAI: Kimi K3","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.112e-7,"completion":0.0000176,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.002e-7,"input_cache_write":0.0,"max_prompt_cost":0.2214592512,"max_completion_cost":16.6094368,"max_cost":16.6315828096},"sats_pricing":{"prompt":0.0002631087028248868,"completion":0.021925725235407232,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00024940512455275723,"input_cache_write":0.0,"max_prompt_cost":275.8894711733085,"max_completion_cost":20691.70156770804,"max_cost":20719.290620068856},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k3-20260715","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"kimi-k3:batch","name":"MoonshotAI: Kimi K3 (batch)","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.5080000000000004e-6,"completion":0.00001254,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.5080000000000005e-7,"input_cache_write":0.0,"max_prompt_cost":2.6298286080000004,"max_completion_cost":0.20545536,"max_cost":2.7941928960000006},"sats_pricing":{"prompt":0.0031244158460455307,"completion":0.015622079230227652,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003124415846045531,"input_cache_write":0.0,"max_prompt_cost":3276.1874701830384,"max_completion_cost":255.95214610804985,"max_cost":3480.9491870694787},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k3-20260715","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"muse-spark-1.1","name":"Meta: Muse Spark 1.1","created":1784215741,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":4.675e-6,"request":0.0,"image":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":1.4417920000000002,"max_completion_cost":4.41188165,"max_cost":4.5560614},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.0058240207656550455,"request":0.001,"image":0.0,"web_search":3.4258945680323802,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":1796.1554112845606,"max_completion_cost":5496.233228922448,"max_cost":5675.849455229818},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.1-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":2.75e-7,"max_prompt_cost":0.231,"max_completion_cost":0.16896,"max_cost":0.3718},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000027407156544259042,"input_cache_write":0.000342589456803238,"max_prompt_cost":287.7751437147199,"max_completion_cost":210.4869622599094,"max_cost":463.18094559797777},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-luna-pro:batch","name":"OpenAI: GPT-5.6 Luna Pro (batch)","created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.1155,"max_completion_cost":0.08448,"max_cost":0.1859},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.0,"max_prompt_cost":143.88757185735994,"max_completion_cost":105.2434811299547,"max_cost":231.59047279898888},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":2.75e-7,"max_prompt_cost":0.231,"max_completion_cost":0.16896,"max_cost":0.3718},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000027407156544259042,"input_cache_write":0.000342589456803238,"max_prompt_cost":287.7751437147199,"max_completion_cost":210.4869622599094,"max_cost":463.18094559797777},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-luna-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-luna:batch","name":"OpenAI: GPT-5.6 Luna (batch)","created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.1155,"max_completion_cost":0.08448,"max_cost":0.1859},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.0,"max_prompt_cost":143.88757185735994,"max_completion_cost":105.2434811299547,"max_cost":231.59047279898888},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-luna-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.6896,"max_cost":3.718},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.016444293926555425,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2877.751437147199,"max_completion_cost":2104.8696225990943,"max_cost":4631.809455979777},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-terra-pro:batch","name":"OpenAI: GPT-5.6 Terra Pro (batch)","created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":1.155,"max_completion_cost":0.8448,"max_cost":1.859},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":1438.8757185735994,"max_completion_cost":1052.4348112995472,"max_cost":2315.9047279898887},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.6896,"max_cost":3.718},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.016444293926555425,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2877.751437147199,"max_completion_cost":2104.8696225990943,"max_cost":4631.809455979777},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-terra-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-terra:batch","name":"OpenAI: GPT-5.6 Terra (batch)","created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":1.155,"max_completion_cost":0.8448,"max_cost":1.859},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":1438.8757185735994,"max_completion_cost":1052.4348112995472,"max_cost":2315.9047279898887},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-terra-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.62,"max_completion_cost":2.8160000000000003,"max_cost":6.8728},"sats_pricing":{"prompt":0.005481431308851808,"completion":0.027407156544259043,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0005481431308851808,"input_cache_write":0.006851789136064761,"max_prompt_cost":5755.502874294398,"max_completion_cost":3508.1160376651574,"max_cost":8561.995704426523},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-sol-pro:batch","name":"OpenAI: GPT-5.6 Sol Pro (batch)","created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2877.751437147199,"max_completion_cost":1754.0580188325787,"max_cost":4280.9978522132615},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.62,"max_completion_cost":2.8160000000000003,"max_cost":6.8728},"sats_pricing":{"prompt":0.005481431308851808,"completion":0.027407156544259043,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0005481431308851808,"input_cache_write":0.006851789136064761,"max_prompt_cost":5755.502874294398,"max_completion_cost":3508.1160376651574,"max_cost":8561.995704426523},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-sol-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.6-sol:batch","name":"OpenAI: GPT-5.6 Sol (batch)","created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2877.751437147199,"max_completion_cost":1754.0580188325787,"max_cost":4280.9978522132615},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-sol-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"grok-4.5","name":"SpaceXAI: Grok 4.5","created":1783523154,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":2.97,"max_cost":3.08},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0004111073481638856,"input_cache_write":0.0,"max_prompt_cost":1370.357827212952,"max_completion_cost":3699.9661334749703,"max_cost":3837.0019161962655},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.5-20260708","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"high"}},{"id":"grok-latest","name":"xAI: Grok Latest","created":1783519360,"description":"This model always redirects to the latest Grok model from xAI.","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":2.97,"max_cost":3.08},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":1370.357827212952,"max_completion_cost":3699.9661334749703,"max_cost":3837.0019161962655},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~x-ai/grok-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"}},{"id":"aion-3.0-mini","name":"AionLabs: Aion-3.0-Mini","created":1783443096,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.7e-7,"completion":1.54e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.9800000000000003e-7,"input_cache_write":0.0,"max_prompt_cost":0.10092544,"max_completion_cost":0.05046272,"max_cost":0.1261568},"sats_pricing":{"prompt":0.0009592504790490664,"completion":0.0019185009580981328,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002466644088983314,"input_cache_write":0.0,"max_prompt_cost":125.73087878991923,"max_completion_cost":62.865439394959616,"max_cost":157.16359848739904},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.0-mini-20260707","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"aion-3.0","name":"AionLabs: Aion-3.0","created":1783443095,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.4325376,"max_completion_cost":0.2162688,"max_cost":0.540672},"sats_pricing":{"prompt":0.004111073481638856,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.001027768370409714,"input_cache_write":0.0,"max_prompt_cost":538.8466233853682,"max_completion_cost":269.4233116926841,"max_cost":673.5582792317102},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.0-20260707","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"hy3","name":"Tencent: Hy3","created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.452e-7,"completion":5.808e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.63e-8,"input_cache_write":0.0,"max_prompt_cost":0.0380633088,"max_completion_cost":0.0743424,"max_cost":0.0938201088},"sats_pricing":{"prompt":0.00018088723319210966,"completion":0.0007235489327684386,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000045221808298027414,"input_cache_write":0.0,"max_prompt_cost":47.418502857912394,"max_completion_cost":92.61426339436015,"max_cost":116.87920040368249},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy3-20260706","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.2,"max_completion_cost":1.4080000000000001,"max_cost":3.3264000000000005},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2740.715654425904,"max_completion_cost":1754.0580188325787,"max_cost":4143.962069491967},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5-20260630","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"claude-sonnet-5:batch","name":"Anthropic: Claude Sonnet 5 (batch)","created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.1,"max_completion_cost":0.7040000000000001,"max_cost":1.6632000000000002},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0017129472840161902,"max_prompt_cost":1370.357827212952,"max_completion_cost":877.0290094162893,"max_cost":2071.9810347459834},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5-20260630","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"gemini-3.1-flash-lite-image","name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","created":1782837225,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"web_search":0.015400000000000002,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.0180224,"max_completion_cost":0.0973203,"max_cost":0.09912264999999999},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.002055536740819428,"request":0.001,"image":0.0,"web_search":19.18500958098133,"internal_reasoning":0.0,"input_cache_read":0.0000342589456803238,"input_cache_write":0.0,"max_prompt_cost":22.451942641057006,"max_completion_cost":121.23966804701149,"max_cost":123.48499934689991},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-image-20260630","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"}},{"id":"fugu-ultra","name":"Sakana: Fugu Ultra","created":1782276303,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000033,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":5.500000000000001,"max_completion_cost":4.224,"max_cost":9.02},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.041110734816388564,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":6851.789136064761,"max_completion_cost":5262.174056497735,"max_cost":11236.934183146204},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/fugu-ultra-20260615","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"xhigh"}},{"id":"gemini-3.1-flash-image","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","created":1781754065,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","context_length":131072,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"web_search":0.015400000000000002,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.0720896,"max_completion_cost":0.1081344,"max_cost":0.1622016},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.004111073481638856,"request":0.001,"image":0.0,"web_search":19.18500958098133,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0,"max_prompt_cost":89.80777056422802,"max_completion_cost":134.71165584634204,"max_cost":202.06748376951305},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-image-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"}},{"id":"gemini-3-pro-image","name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","created":1781754054,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","context_length":131072,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":2.2e-6,"web_search":0.015400000000000002,"internal_reasoning":0.0000132,"input_cache_read":2.2e-7,"input_cache_write":4.125e-7,"max_prompt_cost":0.1441792,"max_completion_cost":0.4325376,"max_cost":0.5046272},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.016444293926555425,"request":0.001,"image":0.002740715654425904,"web_search":19.18500958098133,"internal_reasoning":0.016444293926555425,"input_cache_read":0.0002740715654425904,"input_cache_write":0.000513884185204857,"max_prompt_cost":179.61554112845604,"max_completion_cost":538.8466233853682,"max_cost":628.6543939495962},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-pro-image-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"glm-5.2","name":"Z.ai: GLM 5.2","created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-9,"completion":7.48e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":0.0,"max_prompt_cost":0.0069206016,"max_completion_cost":7.05901064,"max_cost":7.0597027028},"sats_pricing":{"prompt":8.222146963277712e-6,"completion":0.009318433225048073,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.8517891360647605e-6,"input_cache_write":0.0,"max_prompt_cost":8.62154597416589,"max_completion_cost":8793.973166275919,"max_cost":8794.835324162194},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.2-20260616","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","none"],"default_effort":"high"}},{"id":"kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","created":1781266361,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":3.85e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.9083266500000001,"max_cost":0.9256285500000001},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.004796252395245332,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":215.53864935414725,"max_completion_cost":1131.575031357836,"max_cost":1153.1293896220684},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2.7-code-20260612","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true}},{"id":"claude-fable-latest","name":"Anthropic: Claude Fable Latest","created":1781029944,"description":"This model always redirects to the latest model in the Claude Fable family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.000000000000002,"max_completion_cost":7.040000000000001,"max_cost":16.632},"sats_pricing":{"prompt":0.013703578272129521,"completion":0.0685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0171294728401619,"max_prompt_cost":13703.578272129522,"max_completion_cost":8770.290094162894,"max_cost":20719.810347459836},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-fable-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"claude-fable-5","name":"Anthropic: Claude Fable 5","created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.000000000000002,"max_completion_cost":7.040000000000001,"max_cost":16.632},"sats_pricing":{"prompt":0.013703578272129521,"completion":0.0685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.001370357827212952,"input_cache_write":0.0171294728401619,"max_prompt_cost":13703.578272129522,"max_completion_cost":8770.290094162894,"max_cost":20719.810347459836},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-5-fable-20260609","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"claude-fable-5:batch","name":"Anthropic: Claude Fable 5 (batch)","created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.0342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.00856473642008095,"max_prompt_cost":6851.789136064761,"max_completion_cost":4385.145047081447,"max_cost":10359.905173729918},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-5-fable-20260609","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"nemotron-3.5-content-safety","name":"NVIDIA: Nemotron 3.5 Content Safety","created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.025952080000000002,"max_cost":0.02883584},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":35.92310822569121,"max_completion_cost":32.33057814586974,"max_cost":35.92310822569121},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3.5-content-safety-20260604","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.64e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.32e-7,"input_cache_write":0.0,"max_prompt_cost":0.133848,"max_completion_cost":0.4818528,"max_cost":0.4952376},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.003288858785311085,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00016444293926555422,"input_cache_write":0.0,"max_prompt_cost":166.74514041527198,"max_completion_cost":600.2825054949792,"max_cost":616.9570195365063},"per_request_limits":null,"top_provider":{"context_length":202800,"max_completion_tokens":182520,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","none"],"default_effort":"high","supports_max_tokens":true}},{"id":"qwen3.7-plus","name":"Qwen: Qwen3.7 Plus","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":3.5200000000000003e-7,"completion":1.4080000000000001e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.040000000000001e-8,"input_cache_write":4.4e-7,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18454937600000001,"max_cost":0.49041203200000005},"sats_pricing":{"prompt":0.00043851450470814467,"completion":0.0017540580188325787,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008770290094162893,"input_cache_write":0.0005481431308851808,"max_prompt_cost":438.51450470814467,"max_completion_cost":229.90789264442375,"max_cost":610.9454241914625},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-plus-20260602","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"qwen3.7-plus:batch","name":"Qwen: Qwen3.7 Plus (batch)","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.53e-7,"completion":1.012e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.066322432,"max_completion_cost":0.132644864,"max_cost":0.16580608},"sats_pricing":{"prompt":0.00031518230025897893,"completion":0.0012607292010359157,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":82.62314891908977,"max_completion_cost":165.24629783817954,"max_cost":206.55787229772443},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-plus-20260602","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"minimax-m3","name":"MiniMax: MiniMax M3","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.67584,"max_cost":0.67989504},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008222146963277711,"input_cache_write":0.0,"max_prompt_cost":215.53864935414725,"max_completion_cost":841.9478490396376,"max_cost":846.9995361338755},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":512000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m3-20260531","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"step-3.7-flash","name":"StepFun: Step 3.7 Flash","created":1779985069,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.2650000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.05632,"max_completion_cost":0.29145600000000005,"max_cost":0.2970880000000001},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0015759115012948949,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000054814313088518084,"input_cache_write":0.0,"max_prompt_cost":70.16232075330313,"max_completion_cost":363.0900098983438,"max_cost":370.1062419736742},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":230400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"stepfun/step-3.7-flash-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.0342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.00856473642008095,"max_prompt_cost":6851.789136064761,"max_completion_cost":4385.145047081447,"max_cost":10359.905173729918},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.8-opus-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"claude-opus-4.8:batch","name":"Anthropic: Claude Opus 4.8 (batch)","created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":2.7500000000000004,"max_completion_cost":1.7600000000000002,"max_cost":4.158},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.0171294728401619,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.004282368210040475,"max_prompt_cost":3425.8945680323804,"max_completion_cost":2192.5725235407235,"max_cost":5179.952586864959},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.8-opus-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"qwen3.7-max","name":"Qwen: Qwen3.7 Max","created":1779376861,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.6225000000000001e-6,"completion":4.8675e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.2450000000000003e-7,"input_cache_write":2.028125e-6,"max_prompt_cost":1.6225,"max_completion_cost":0.63799296,"max_cost":2.04782864},"sats_pricing":{"prompt":0.0020212777951391044,"completion":0.006063833385417313,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00040425555902782085,"input_cache_write":0.0025265972439238804,"max_prompt_cost":2021.2777951391042,"max_completion_cost":794.798769493418,"max_cost":2551.1436414680493},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-max-20260520","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"grok-build-0.1","name":"SpaceXAI: Grok Build 0.1","created":1779298123,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...","context_length":256000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":0.50688,"max_cost":0.53504},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":350.8116037665157,"max_completion_cost":631.4608867797282,"max_cost":666.5420471563798},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":230400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-build-0.1-20260520","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":9.900000000000002e-6,"request":0.0,"image":1.65e-6,"web_search":0.015400000000000002,"internal_reasoning":9.900000000000002e-6,"input_cache_read":1.65e-7,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":1.7301504,"max_completion_cost":0.6488064000000001,"max_cost":2.2708224},"sats_pricing":{"prompt":0.002055536740819428,"completion":0.01233322044491657,"request":0.001,"image":0.002055536740819428,"web_search":19.18500958098133,"internal_reasoning":0.01233322044491657,"input_cache_read":0.0002055536740819428,"input_cache_write":0.00011419648560107929,"max_prompt_cost":2155.3864935414726,"max_completion_cost":808.2699350780523,"max_cost":2828.9447727731826},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-20260519","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gemini-3.5-flash:batch","name":"Google: Gemini 3.5 Flash (batch)","created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.950000000000001e-6,"request":0.0,"image":8.25e-7,"web_search":0.015400000000000002,"internal_reasoning":4.950000000000001e-6,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.8650752,"max_completion_cost":0.32440320000000006,"max_cost":1.1354112},"sats_pricing":{"prompt":0.001027768370409714,"completion":0.006166610222458285,"request":0.001,"image":0.001027768370409714,"web_search":19.18500958098133,"internal_reasoning":0.006166610222458285,"input_cache_read":0.0001027768370409714,"input_cache_write":0.0,"max_prompt_cost":1077.6932467707363,"max_completion_cost":404.13496753902615,"max_cost":1414.4723863865913},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-20260519","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"perceptron-mk1","name":"Perceptron: Perceptron Mk1","created":1778597029,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","context_length":32768,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00540672,"max_completion_cost":0.0135168,"max_cost":0.017571840000000002},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.002055536740819428,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.735582792317102,"max_completion_cost":16.838956980792755,"max_cost":21.890644075030583},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perceptron/perceptron-mk1-20260512","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.65e-6,"request":0.0,"image":2.75e-7,"web_search":0.015400000000000002,"internal_reasoning":1.65e-6,"input_cache_read":2.75e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.2883584,"max_completion_cost":0.1081344,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.002055536740819428,"request":0.001,"image":0.000342589456803238,"web_search":19.18500958098133,"internal_reasoning":0.002055536740819428,"input_cache_read":0.0000342589456803238,"input_cache_write":0.00011419648560107929,"max_prompt_cost":359.2310822569121,"max_completion_cost":134.71165584634204,"max_cost":471.4907954621971},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-20260507","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"}},{"id":"gemini-3.1-flash-lite:batch","name":"Google: Gemini 3.1 Flash Lite (batch)","created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.375e-7,"completion":8.25e-7,"request":0.0,"image":1.375e-7,"web_search":0.015400000000000002,"internal_reasoning":8.25e-7,"input_cache_read":1.375e-8,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.0540672,"max_cost":0.18923520000000002},"sats_pricing":{"prompt":0.000171294728401619,"completion":0.001027768370409714,"request":0.001,"image":0.000171294728401619,"web_search":19.18500958098133,"internal_reasoning":0.001027768370409714,"input_cache_read":0.0000171294728401619,"input_cache_write":0.0,"max_prompt_cost":179.61554112845604,"max_completion_cost":67.35582792317102,"max_cost":235.74539773109856},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-20260507","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"}},{"id":"gpt-chat-latest","name":"OpenAI: GPT Chat Latest","created":1778000212,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000033,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":2.2,"max_completion_cost":4.224,"max_cost":5.720000000000001},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.041110734816388564,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":2740.715654425904,"max_completion_cost":5262.174056497735,"max_cost":7125.86070150735},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-chat-latest-20260505","alias_ids":null,"forwarded_model_id":null},{"id":"grok-4.3","name":"SpaceXAI: Grok 4.3","created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":1.3750000000000002,"max_completion_cost":2.4750000000000005,"max_cost":2.6125000000000007},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":1712.9472840161902,"max_completion_cost":3083.3051112291423,"max_cost":3254.599839630762},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":900000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.3-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"low"}},{"id":"grok-4.3:batch","name":"SpaceXAI: Grok 4.3 (batch)","created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":1.7600000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":1.9800000000000002,"max_cost":2.0900000000000003},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.00021925725235407234,"input_cache_write":0.0,"max_prompt_cost":1370.357827212952,"max_completion_cost":2466.644088983314,"max_cost":2603.679871704609},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":900000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.3-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"low"}},{"id":"mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.4325376,"max_completion_cost":1.7301487500000001,"max_cost":1.8166566000000002},"sats_pricing":{"prompt":0.002055536740819428,"completion":0.010277683704097141,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":538.8466233853682,"max_completion_cost":2155.3844380047317,"max_cost":2263.1541737891534},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3.5-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","none"],"default_effort":"high"}},{"id":"mistral-medium-3-5:batch","name":"Mistral: Mistral Medium 3.5 (batch)","created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.125e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2162688,"max_completion_cost":0.8650743750000001,"max_cost":0.9083283000000001},"sats_pricing":{"prompt":0.001027768370409714,"completion":0.0051388418520485705,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":269.4233116926841,"max_completion_cost":1077.6922190023658,"max_cost":1131.5770868945767},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3.5-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","none"],"default_effort":"high"}},{"id":"claude-haiku-latest","name":"Anthropic: Claude Haiku Latest","created":1777318492,"description":"This model always redirects to the latest model in the Claude Haiku family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.11,"max_completion_cost":0.0704,"max_cost":0.16632000000000002},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.000171294728401619,"max_prompt_cost":137.0357827212952,"max_completion_cost":87.70290094162893,"max_cost":207.19810347459835},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-haiku-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-mini-latest","name":"OpenAI: GPT Mini Latest","created":1777318471,"description":"This model always redirects to the latest model in the GPT Mini family.","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.950000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.6336000000000002,"max_cost":0.8580000000000002},"sats_pricing":{"prompt":0.001027768370409714,"completion":0.006166610222458285,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001027768370409714,"input_cache_write":0.0,"max_prompt_cost":411.1073481638856,"max_completion_cost":789.3261084746605,"max_cost":1068.8791052261026},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-mini-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gemini-pro-latest","name":"Google: Gemini Pro Latest","created":1777318451,"description":"This model always redirects to the latest model in the Gemini Pro family.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":2.2e-6,"web_search":0.015400000000000002,"internal_reasoning":0.000011000000000000001,"input_cache_read":1.1e-7,"input_cache_write":2.0625e-7,"max_prompt_cost":2.3068672,"max_completion_cost":10.380898000000002,"max_cost":10.611585600000002},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.002740715654425904,"web_search":19.18500958098133,"internal_reasoning":0.013703578272129521,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0002569420926024285,"max_prompt_cost":2873.8486580552967,"max_completion_cost":12932.313479817529,"max_cost":13219.699441909319},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~google/gemini-pro-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"kimi-latest","name":"MoonshotAI: Kimi Latest","created":1777318428,"description":"This model always redirects to the latest model in the Kimi family.","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.7138000000000002e-7,"completion":0.00001160258,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.17970495488000002,"max_completion_cost":10.94956359244,"max_cost":10.967534156480001},"sats_pricing":{"prompt":0.00021350174947977794,"completion":0.014454260289876774,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":223.87281046250763,"max_completion_cost":13640.74561224193,"max_cost":13663.132978688882},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~moonshotai/kimi-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"gemini-flash-latest","name":"Google: Gemini Flash Latest","created":1777318398,"description":"This model always redirects to the latest model in the Gemini Flash family.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.125e-6,"request":0.0,"image":8.25e-7,"web_search":0.015400000000000002,"internal_reasoning":4.125e-6,"input_cache_read":8.25e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.8650752,"max_completion_cost":0.270336,"max_cost":1.081344},"sats_pricing":{"prompt":0.001027768370409714,"completion":0.0051388418520485705,"request":0.001,"image":0.001027768370409714,"web_search":19.18500958098133,"internal_reasoning":0.0051388418520485705,"input_cache_read":0.0001027768370409714,"input_cache_write":0.00005709824280053971,"max_prompt_cost":1077.6932467707363,"max_completion_cost":336.7791396158551,"max_cost":1347.1165584634205},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~google/gemini-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"claude-sonnet-latest","name":"Anthropic: Claude Sonnet Latest","created":1777318368,"description":"This model always redirects to the latest model in the Claude Sonnet family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.2,"max_completion_cost":1.4080000000000001,"max_cost":3.3264000000000005},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0034258945680323803,"max_prompt_cost":2740.715654425904,"max_completion_cost":1754.0580188325787,"max_cost":4143.962069491967},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-sonnet-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","created":1777261368,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.98e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":4.125e-7,"max_prompt_cost":0.33,"max_completion_cost":0.12976128,"max_cost":0.43813440000000003},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0024666440889833134,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.000513884185204857,"max_prompt_cost":411.1073481638856,"max_completion_cost":161.65398701561043,"max_cost":545.8190040102277},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-plus-20260420","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","created":1777261362,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.0625e-7,"completion":1.2375000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":2.578125e-7,"max_prompt_cost":0.20625000000000002,"max_completion_cost":0.08110080000000001,"max_cost":0.273834},"sats_pricing":{"prompt":0.0002569420926024285,"completion":0.0015416525556145712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.00032117761575303566,"max_prompt_cost":256.9420926024285,"max_completion_cost":101.03374188475654,"max_cost":341.1368775063923},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-flash","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","created":1777260255,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.23356971,"max_cost":0.23645336},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0012333220444916567,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000342589456803238,"input_cache_write":0.0,"max_prompt_cost":35.92310822569121,"max_completion_cost":290.9764366348721,"max_cost":294.56882967891084},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-35b-a3b-20260415","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"qwen3.6-27b","name":"Qwen: Qwen3.6 27B","created":1777255064,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":4.95e-7,"completion":2.9700000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.12976128,"max_completion_cost":0.19464192000000002,"max_cost":0.29196288000000004},"sats_pricing":{"prompt":0.0006166610222458283,"completion":0.0036999661334749705,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":161.65398701561043,"max_completion_cost":242.48098052341567,"max_cost":363.72147078512353},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-27b-20260422","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro","created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000033,"completion":0.00019800000000000002,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":34.650000000000006,"max_completion_cost":25.344,"max_cost":55.77},"sats_pricing":{"prompt":0.041110734816388564,"completion":0.24666440889833136,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":43166.27155720799,"max_completion_cost":31573.044338986412,"max_cost":69477.14183969666},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.5-pro-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"}},{"id":"gpt-5.5-pro:batch","name":"OpenAI: GPT-5.5 Pro (batch)","created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000165,"completion":0.00009900000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":17.325000000000003,"max_completion_cost":12.672,"max_cost":27.885},"sats_pricing":{"prompt":0.020555367408194282,"completion":0.12333220444916568,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":21583.135778603995,"max_completion_cost":15786.522169493206,"max_cost":34738.57091984833},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.5-pro-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"}},{"id":"gpt-5.5","name":"OpenAI: GPT-5.5","created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000033,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":5.775,"max_completion_cost":4.224,"max_cost":9.295000000000002},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.041110734816388564,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":7194.378592867998,"max_completion_cost":5262.174056497735,"max_cost":11579.523639949446},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.5-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.5:batch","name":"OpenAI: GPT-5.5 (batch)","created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.8875,"max_completion_cost":2.112,"max_cost":4.647500000000001},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":3597.189296433999,"max_completion_cost":2631.0870282488677,"max_cost":5789.761819974723},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.5-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","created":1777000679,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.76e-6,"completion":3.52e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.485e-7,"input_cache_write":0.0,"max_prompt_cost":1.84549376,"max_completion_cost":1.38412032,"max_cost":2.53755392},"sats_pricing":{"prompt":0.002192572523540723,"completion":0.004385145047081446,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018499830667374854,"input_cache_write":0.0,"max_prompt_cost":2299.0789264442374,"max_completion_cost":1724.309194833178,"max_cost":3161.233523860826},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-pro-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","none"],"default_effort":"high"}},{"id":"deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.001e-7,"completion":2.002e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.0020000000000003e-8,"input_cache_write":0.0,"max_prompt_cost":0.1049623575,"max_completion_cost":0.1889321434,"max_cost":0.1994284292},"sats_pricing":{"prompt":0.00012470256227637861,"completion":0.00024940512455275723,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002494051245527573,"input_cache_write":0.0,"max_prompt_cost":130.75998923895372,"max_completion_cost":235.36785592755442,"max_cost":248.44391720273094},"per_request_limits":null,"top_provider":{"context_length":1048575,"max_completion_tokens":943717,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-flash-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","none"],"default_effort":"high"}},{"id":"hy3-preview","name":"Tencent: Hy3 preview","created":1776878150,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.9800000000000003e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.05190451200000001,"max_completion_cost":0.15571314,"max_cost":0.16090371},"sats_pricing":{"prompt":0.0002466644088983314,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008222146963277711,"input_cache_write":0.0,"max_prompt_cost":64.66159480624418,"max_completion_cost":193.9842910899147,"max_cost":200.45059856918448},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy3-preview-20260421","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","created":1776874273,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","context_length":1050000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.28e-7,"completion":1.98e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.056e-7,"input_cache_write":0.0,"max_prompt_cost":0.138412032,"max_completion_cost":0.46713942,"max_cost":0.48098094},"sats_pricing":{"prompt":0.0006577717570622169,"completion":0.0024666440889833134,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001315543514124434,"input_cache_write":0.0,"max_prompt_cost":172.43091948331778,"max_completion_cost":581.9528732697441,"max_cost":599.1963598811302},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.5-pro-20260422","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"mimo-v2.5","name":"Xiaomi: MiMo-V2.5","created":1776874269,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","context_length":1000000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.800000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.44,"max_completion_cost":0.1441792,"max_cost":0.55534336},"sats_pricing":{"prompt":0.0005481431308851808,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00010962862617703617,"input_cache_write":0.0,"max_prompt_cost":548.1431308851808,"max_completion_cost":179.61554112845604,"max_cost":691.8355637879455},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.5-20260422","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gpt-5.4-image-2","name":"OpenAI: GPT-5.4 Image 2","created":1776797528,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","context_length":272000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.8e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-6,"input_cache_write":0.0,"max_prompt_cost":2.3936,"max_completion_cost":2.112,"max_cost":3.3792},"sats_pricing":{"prompt":0.010962862617703616,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.002740715654425904,"input_cache_write":0.0,"max_prompt_cost":2981.8986320153836,"max_completion_cost":2631.0870282488677,"max_cost":4209.739245198189},"per_request_limits":null,"top_provider":{"context_length":272000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-image-2-20260421","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"claude-opus-latest","name":"Anthropic: Claude Opus Latest","created":1776795361,"description":"This model always redirects to the latest model in the Claude Opus family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.4,"max_completion_cost":2.8160000000000003,"max_cost":6.652800000000001},"sats_pricing":{"prompt":0.005481431308851808,"completion":0.027407156544259043,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.006851789136064761,"max_prompt_cost":5481.431308851808,"max_completion_cost":3508.1160376651574,"max_cost":8287.924138983934},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-opus-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"kimi-k2.6","name":"MoonshotAI: Kimi K2.6","created":1776699402,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.15e-7,"completion":3.751e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.18743296,"max_completion_cost":0.884969679,"max_cost":0.903713404},"sats_pricing":{"prompt":0.0008907325876884187,"completion":0.004672920190796166,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":233.50020346699284,"max_completion_cost":1102.4773876943486,"max_cost":1125.8279424806005},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2.6-20260420","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.0342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.00856473642008095,"max_prompt_cost":6851.789136064761,"max_completion_cost":4385.145047081447,"max_cost":10359.905173729918},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.7-opus-20260416","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"claude-opus-4.7:batch","name":"Anthropic: Claude Opus 4.7 (batch)","created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":2.7500000000000004,"max_completion_cost":1.7600000000000002,"max_cost":4.158},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.0171294728401619,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.004282368210040475,"max_prompt_cost":3425.8945680323804,"max_completion_cost":2192.5725235407235,"max_cost":5179.952586864959},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.7-opus-20260416","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"}},{"id":"glm-5.1","name":"Z.ai: GLM 5.1","created":1775578025,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.54e-6,"completion":4.84e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.8600000000000005e-7,"input_cache_write":0.0,"max_prompt_cost":0.31223808000000003,"max_completion_cost":0.63438848,"max_cost":0.74477568},"sats_pricing":{"prompt":0.0019185009580981328,"completion":0.006029574439736988,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00035629303507536756,"input_cache_write":0.0,"max_prompt_cost":388.97990625631263,"max_completion_cost":790.3083809652065,"max_cost":927.8265296416807},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.1-20260406","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","created":1775227989,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":3.850000000000001e-8,"completion":1.1440000000000002e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.8700000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.010092544000000002,"max_completion_cost":0.0037486592000000006,"max_cost":0.012579635200000001},"sats_pricing":{"prompt":0.00004796252395245332,"completion":0.00014251721403014703,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000023296083062620186,"input_cache_write":0.0,"max_prompt_cost":12.573087878991924,"max_completion_cost":4.670004069339858,"max_cost":15.67145596345779},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-4-26b-a4b-it-20260403","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"gemma-4-31b-it","name":"Google: Gemma 4 31B","created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.00720896,"max_cost":0.06127616},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0005481431308851808,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":71.84621645138242,"max_completion_cost":8.980777056422802,"max_cost":76.33660497959382},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-4-31b-it-20260402","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"qwen3.6-plus","name":"Qwen: Qwen3.6 Plus","created":1775133557,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.575e-7,"completion":2.1450000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":4.46875e-7,"max_prompt_cost":0.35750000000000004,"max_completion_cost":0.14057472000000001,"max_cost":0.4746456},"sats_pricing":{"prompt":0.00044536629384420937,"completion":0.0026721977630652567,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0005567078673052617,"max_prompt_cost":445.3662938442094,"max_completion_cost":175.12515260024466,"max_cost":591.3039210110799},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-plus-04-02","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","created":1775061458,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","context_length":202752,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.64e-7,"input_cache_write":0.0,"max_prompt_cost":0.26763264000000003,"max_completion_cost":0.5767168,"max_cost":0.6713344},"sats_pricing":{"prompt":0.0016444293926555424,"completion":0.005481431308851808,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00032888587853110844,"input_cache_write":0.0,"max_prompt_cost":333.41134821969655,"max_completion_cost":718.4621645138242,"max_cost":836.3348633793734},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5v-turbo-20260401","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"grok-4.20-multi-agent","name":"SpaceXAI: Grok 4.20 Multi-Agent","created":1774979158,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","context_length":2000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":2.7500000000000004,"max_completion_cost":4.950000000000001,"max_cost":5.225000000000001},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":3425.8945680323804,"max_completion_cost":6166.610222458285,"max_cost":6509.199679261524},"per_request_limits":null,"top_provider":{"context_length":2000000,"max_completion_tokens":1800000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.20-multi-agent-20260309","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"grok-4.20","name":"SpaceXAI: Grok 4.20","created":1774979019,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","context_length":2000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":2.7500000000000004,"max_completion_cost":4.950000000000001,"max_cost":5.225000000000001},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":3425.8945680323804,"max_completion_cost":6166.610222458285,"max_cost":6509.199679261524},"per_request_limits":null,"top_provider":{"context_length":2000000,"max_completion_tokens":1800000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.20-20260309","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"reka-edge","name":"Reka Edge","created":1774026965,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...","context_length":16384,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":1.1e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00180224,"max_completion_cost":0.00162195,"max_cost":0.00180224},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.2451942641057006,"max_completion_cost":2.0205926162254975,"max_cost":2.2451942641057006},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":14745,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"rekaai/reka-edge-2603","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"minimax-m2.7","name":"MiniMax: MiniMax M2.7","created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.067584,"max_completion_cost":0.17301504,"max_cost":0.19734528},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008222146963277711,"input_cache_write":0.0,"max_prompt_cost":84.19478490396378,"max_completion_cost":215.53864935414725,"max_cost":245.8487719195742},"per_request_limits":null,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2.7-20260318","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.08800000000000001,"max_completion_cost":0.17600000000000002,"max_cost":0.23584000000000002},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0017129472840161902,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000027407156544259042,"input_cache_write":0.0,"max_prompt_cost":109.62862617703617,"max_completion_cost":219.25725235407234,"max_cost":293.8047181544569},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-nano-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.4-nano:batch","name":"OpenAI: GPT-5.4 Nano (batch)","created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":6.875000000000001e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.044000000000000004,"max_completion_cost":0.08800000000000001,"max_cost":0.11792000000000001},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0008564736420080951,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.0,"max_prompt_cost":54.814313088518084,"max_completion_cost":109.62862617703617,"max_cost":146.90235907722845},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-nano-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.950000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.6336000000000002,"max_cost":0.8580000000000002},"sats_pricing":{"prompt":0.001027768370409714,"completion":0.006166610222458285,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001027768370409714,"input_cache_write":0.0,"max_prompt_cost":411.1073481638856,"max_completion_cost":789.3261084746605,"max_cost":1068.8791052261026},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-mini-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.4-mini:batch","name":"OpenAI: GPT-5.4 Mini (batch)","created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":2.4750000000000004e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.165,"max_completion_cost":0.3168000000000001,"max_cost":0.4290000000000001},"sats_pricing":{"prompt":0.000513884185204857,"completion":0.0030833051112291424,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000513884185204857,"input_cache_write":0.0,"max_prompt_cost":205.5536740819428,"max_completion_cost":394.66305423733024,"max_cost":534.4395526130513},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-mini-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"mistral-small-2603","name":"Mistral: Mistral Small 4","created":1773695685,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.1384119,"max_cost":0.147062685},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000020555367408194277,"input_cache_write":0.0,"max_prompt_cost":53.88466233853681,"max_completion_cost":172.43075504037853,"max_cost":183.2077286188207},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-2603","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","none"],"default_effort":"high"}},{"id":"glm-5-turbo","name":"Z.ai: GLM 5 Turbo","created":1773583573,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.64e-7,"input_cache_write":0.0,"max_prompt_cost":0.26763264000000003,"max_completion_cost":0.5767168,"max_cost":0.6713344},"sats_pricing":{"prompt":0.0016444293926555424,"completion":0.005481431308851808,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00032888587853110844,"input_cache_write":0.0,"max_prompt_cost":333.41134821969655,"max_completion_cost":718.4621645138242,"max_cost":836.3348633793734},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5-turbo-20260315","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.64e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.34603008,"max_completion_cost":0.69206016,"max_cost":0.95158272},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.003288858785311085,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":431.0772987082945,"max_completion_cost":862.154597416589,"max_cost":1185.4625714478098},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3-super-120b-a12b-20230311","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["medium","low","none"],"default_effort":"medium","supports_max_tokens":true}},{"id":"seed-2.0-lite","name":"ByteDance Seed: Seed-2.0-Lite","created":1773157231,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0720896,"max_completion_cost":0.2883584,"max_cost":0.3244032},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":89.80777056422802,"max_completion_cost":359.2310822569121,"max_cost":404.1349675390261},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2.0-lite-20260309","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"}},{"id":"qwen3.5-9b","name":"Qwen: Qwen3.5-9B","created":1773152396,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.87e-7,"completion":2.75e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.049020928,"max_completion_cost":0.064880475,"max_cost":0.06978268000000001},"sats_pricing":{"prompt":0.00023296083062620182,"completion":0.000342589456803238,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":61.06928398367505,"max_completion_cost":80.82678795413113,"max_cost":86.93385612899704},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-9b-20260310","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000033,"completion":0.00019800000000000002,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":34.650000000000006,"max_completion_cost":25.344,"max_cost":55.77},"sats_pricing":{"prompt":0.041110734816388564,"completion":0.24666440889833136,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":43166.27155720799,"max_completion_cost":31573.044338986412,"max_cost":69477.14183969666},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-pro-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"}},{"id":"gpt-5.4-pro:batch","name":"OpenAI: GPT-5.4 Pro (batch)","created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000165,"completion":0.00009900000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":17.325000000000003,"max_completion_cost":12.672,"max_cost":27.885},"sats_pricing":{"prompt":0.020555367408194282,"completion":0.12333220444916568,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":21583.135778603995,"max_completion_cost":15786.522169493206,"max_cost":34738.57091984833},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-pro-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"}},{"id":"gpt-5.4","name":"OpenAI: GPT-5.4","created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.8875,"max_completion_cost":2.112,"max_cost":4.647500000000001},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":3597.189296433999,"max_completion_cost":2631.0870282488677,"max_cost":5789.761819974723},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.4:batch","name":"OpenAI: GPT-5.4 (batch)","created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":1.44375,"max_completion_cost":1.056,"max_cost":2.3237500000000004},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.010277683704097141,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000171294728401619,"input_cache_write":0.0,"max_prompt_cost":1798.5946482169995,"max_completion_cost":1315.5435141244338,"max_cost":2894.8809099873615},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"mercury-2","name":"Inception: Mercury 2","created":1772636275,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":8.25e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.0352,"max_completion_cost":0.04125,"max_cost":0.0627},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.001027768370409714,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000342589456803238,"input_cache_write":0.0,"max_prompt_cost":43.85145047081446,"max_completion_cost":51.3884185204857,"max_cost":78.11039615113826},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":50000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inception/mercury-2-20260304","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"}},{"id":"gemini-3.1-flash-lite-preview","name":"Google: Gemini 3.1 Flash Lite Preview","created":1772512673,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.65e-6,"request":0.0,"image":2.75e-7,"web_search":0.015400000000000002,"internal_reasoning":1.65e-6,"input_cache_read":2.75e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.2883584,"max_completion_cost":0.1081344,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.002055536740819428,"request":0.001,"image":0.000342589456803238,"web_search":19.18500958098133,"internal_reasoning":0.002055536740819428,"input_cache_read":0.0000342589456803238,"input_cache_write":0.00011419648560107929,"max_prompt_cost":359.2310822569121,"max_completion_cost":134.71165584634204,"max_cost":471.4907954621971},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-preview-20260303","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"}},{"id":"seed-2.0-mini","name":"ByteDance Seed: Seed-2.0-Mini","created":1772131107,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.05767168,"max_cost":0.0720896},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0005481431308851808,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":35.92310822569121,"max_completion_cost":71.84621645138242,"max_cost":89.80777056422802},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2.0-mini-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"}},{"id":"gemini-3.1-flash-image-preview","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","created":1772119558,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"web_search":0.015400000000000002,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.0360448,"max_completion_cost":0.1946406,"max_cost":0.19824529999999999},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.004111073481638856,"request":0.001,"image":0.0,"web_search":19.18500958098133,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0,"max_prompt_cost":44.90388528211401,"max_completion_cost":242.47933609402298,"max_cost":246.96999869379982},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-image-preview-20260226","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"}},{"id":"qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","created":1772053822,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.5400000000000003e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.04037017600000001,"max_completion_cost":0.090112,"max_cost":0.117866496},"sats_pricing":{"prompt":0.0001918500958098133,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0,"max_prompt_cost":50.292351515967695,"max_completion_cost":112.25971320528502,"max_cost":146.83570487251282},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":81920,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-35b-a3b-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3.5-27b","name":"Qwen: Qwen3.5-27B","created":1772053810,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.8600000000000005e-7,"completion":2.86e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.07497318400000001,"max_completion_cost":0.2342912,"max_cost":0.28583526400000003},"sats_pricing":{"prompt":0.00035629303507536756,"completion":0.003562930350753675,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":93.40008138679715,"max_completion_cost":291.87525433374105,"max_cost":356.08781028716413},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":81920,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-27b-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","created":1772053789,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.8600000000000005e-7,"completion":2.2880000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.07497318400000001,"max_completion_cost":0.14994636800000002,"max_cost":0.20617625600000003},"sats_pricing":{"prompt":0.00035629303507536756,"completion":0.0028503442806029405,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":93.40008138679715,"max_completion_cost":186.8001627735943,"max_cost":256.85022381369214},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-122b-a10b-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","created":1772053776,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":7.150000000000001e-8,"completion":2.8600000000000005e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.07150000000000001,"max_completion_cost":0.018743296000000003,"max_cost":0.08555747200000002},"sats_pricing":{"prompt":0.00008907325876884189,"completion":0.00035629303507536756,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":89.07325876884188,"max_completion_cost":23.35002034669929,"max_cost":106.58577402886637},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-flash-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gemini-3.1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","created":1772045923,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":2.2e-6,"web_search":0.015400000000000002,"internal_reasoning":0.0000132,"input_cache_read":2.2e-7,"input_cache_write":4.125e-7,"max_prompt_cost":2.3068672,"max_completion_cost":0.8650752,"max_cost":3.0277632000000003},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.016444293926555425,"request":0.001,"image":0.002740715654425904,"web_search":19.18500958098133,"internal_reasoning":0.016444293926555425,"input_cache_read":0.0002740715654425904,"input_cache_write":0.000513884185204857,"max_prompt_cost":2873.8486580552967,"max_completion_cost":1077.6932467707363,"max_cost":3771.926363697577},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-pro-preview-customtools-20260219","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","created":1771959164,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.7700000000000001,"max_completion_cost":1.9712000000000003,"max_cost":2.4948000000000006},"sats_pricing":{"prompt":0.002398126197622666,"completion":0.01918500958098133,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002398126197622666,"input_cache_write":0.0,"max_prompt_cost":959.2504790490665,"max_completion_cost":2455.68122636561,"max_cost":3107.9715521189755},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.3-codex-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"aion-2.0","name":"AionLabs: Aion-2.0","created":1771881306,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":1.76e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.11534336,"max_completion_cost":0.05767168,"max_cost":0.1441792},"sats_pricing":{"prompt":0.0010962862617703616,"completion":0.002192572523540723,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":143.69243290276484,"max_completion_cost":71.84621645138242,"max_cost":179.61554112845604},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-2.0-20260223","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":2.2e-6,"web_search":0.015400000000000002,"internal_reasoning":0.0000132,"input_cache_read":2.2e-7,"input_cache_write":4.125e-7,"max_prompt_cost":2.3068672,"max_completion_cost":0.8650752,"max_cost":3.0277632000000003},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.016444293926555425,"request":0.001,"image":0.002740715654425904,"web_search":19.18500958098133,"internal_reasoning":0.016444293926555425,"input_cache_read":0.0002740715654425904,"input_cache_write":0.000513884185204857,"max_prompt_cost":2873.8486580552967,"max_completion_cost":1077.6932467707363,"max_cost":3771.926363697577},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-pro-preview-20260219","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"gemini-3.1-pro-preview:batch","name":"Google: Gemini 3.1 Pro Preview (batch)","created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":6.6e-6,"request":0.0,"image":1.1e-6,"web_search":0.015400000000000002,"internal_reasoning":6.6e-6,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.1534336,"max_completion_cost":0.4325376,"max_cost":1.5138816000000002},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.008222146963277712,"request":0.001,"image":0.001370357827212952,"web_search":19.18500958098133,"internal_reasoning":0.008222146963277712,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1436.9243290276484,"max_completion_cost":538.8466233853682,"max_cost":1885.9631818487885},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-pro-preview-20260219","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":4.125e-6,"max_prompt_cost":3.3000000000000003,"max_completion_cost":2.112,"max_cost":4.9896},"sats_pricing":{"prompt":0.004111073481638856,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0004111073481638856,"input_cache_write":0.0051388418520485705,"max_prompt_cost":4111.073481638856,"max_completion_cost":2631.0870282488677,"max_cost":6215.94310423795},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"medium"}},{"id":"claude-sonnet-4.6:batch","name":"Anthropic: Claude Sonnet 4.6 (batch)","created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":2.0625e-6,"max_prompt_cost":1.6500000000000001,"max_completion_cost":1.056,"max_cost":2.4948},"sats_pricing":{"prompt":0.002055536740819428,"completion":0.010277683704097141,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0025694209260242852,"max_prompt_cost":2055.536740819428,"max_completion_cost":1315.5435141244338,"max_cost":3107.971552118975},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"medium"}},{"id":"qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","created":1771229416,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.8600000000000005e-7,"completion":1.7160000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.28600000000000003,"max_completion_cost":0.11245977600000001,"max_cost":0.3797164800000001},"sats_pricing":{"prompt":0.00035629303507536756,"completion":0.002137758210452205,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":356.2930350753675,"max_completion_cost":140.10012208019572,"max_cost":473.043136808864},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-plus-20260216","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","created":1771223018,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.96e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.93427884,"max_cost":0.94869709},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.004933288177966627,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0004111073481638856,"input_cache_write":0.0,"max_prompt_cost":179.61554112845604,"max_completion_cost":1163.9057465394883,"max_cost":1181.8677117596822},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-397b-a17b-20260216","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"minimax-m2.5","name":"MiniMax: MiniMax M2.5","created":1770908502,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.97e-7,"completion":1.0450000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":4.125e-7,"max_prompt_cost":0.058806000000000004,"max_completion_cost":0.034242560000000005,"max_cost":0.083316464},"sats_pricing":{"prompt":0.00036999661334749707,"completion":0.0013018399358523045,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.000513884185204857,"max_prompt_cost":73.25932944280441,"max_completion_cost":42.65869101800831,"max_cost":103.79397143464195},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2.5-20260211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"glm-5","name":"Z.ai: GLM 5","created":1770829182,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":3.52e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.2230272,"max_completion_cost":0.46137344,"max_cost":0.54022144},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.004385145047081446,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":277.8427901830804,"max_completion_cost":574.7697316110593,"max_cost":672.9969806656837},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5-20260211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.0342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.00856473642008095,"max_prompt_cost":6851.789136064761,"max_completion_cost":4385.145047081447,"max_cost":10359.905173729918},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-opus-20260205","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"high","supports_max_tokens":true}},{"id":"claude-opus-4.6:batch","name":"Anthropic: Claude Opus 4.6 (batch)","created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":2.7500000000000004,"max_completion_cost":1.7600000000000002,"max_cost":4.158},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.0171294728401619,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.004282368210040475,"max_prompt_cost":3425.8945680323804,"max_completion_cost":2192.5725235407235,"max_cost":5179.952586864959},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-opus-20260205","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"high","supports_max_tokens":true}},{"id":"qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","created":1770164101,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":8.8e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.700000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.034603008,"max_completion_cost":0.20761752,"max_cost":0.2110779},"sats_pricing":{"prompt":0.00016444293926555422,"completion":0.0010962862617703616,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009592504790490665,"input_cache_write":0.0,"max_prompt_cost":43.107729870829445,"max_completion_cost":258.6457214532196,"max_cost":262.9565931060661},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-next-2025-02-03","alias_ids":null,"forwarded_model_id":null},{"id":"step-3.5-flash","name":"StepFun: Step 3.5 Flash","created":1769728337,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":3.3e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.02162688,"max_cost":0.04325376},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":35.92310822569121,"max_completion_cost":26.942331169268407,"max_cost":53.88466233853681},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"stepfun/step-3.5-flash","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"kimi-k2.5","name":"MoonshotAI: Kimi K2.5","created":1769487076,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.64880475,"max_cost":0.663223},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":179.61554112845604,"max_completion_cost":808.2678795413113,"max_cost":826.2298447615051},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2.5-0127","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"minimax-m2-her","name":"MiniMax: MiniMax M2-her","created":1769177239,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.00270336,"max_cost":0.0236544},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":26.942331169268407,"max_completion_cost":3.367791396158551,"max_cost":29.468174716387317},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":2048,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2-her-20260123","alias_ids":null,"forwarded_model_id":null},{"id":"palmyra-x5","name":"Writer: Palmyra X5","created":1769003823,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...","context_length":1040000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.6864,"max_completion_cost":0.0540672,"max_cost":0.73506048},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":855.103284180882,"max_completion_cost":67.35582792317102,"max_cost":915.7235293117359},"per_request_limits":null,"top_provider":{"context_length":1040000,"max_completion_tokens":8192,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"writer/palmyra-x5-20250428","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-audio","name":"OpenAI: GPT Audio","created":1768862569,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18022400000000002,"max_cost":0.48716800000000005},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":438.51450470814467,"max_completion_cost":224.51942641057008,"max_cost":606.9040745160722},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-audio","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-audio-mini","name":"OpenAI: GPT Audio Mini","created":1768859419,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.64e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.08448,"max_completion_cost":0.04325376,"max_cost":0.11692032000000001},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.003288858785311085,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":105.2434811299547,"max_completion_cost":53.88466233853681,"max_cost":145.65697788385734},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-audio-mini","alias_ids":null,"forwarded_model_id":null},{"id":"glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","created":1768833913,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.655000000000001e-8,"completion":4.4e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.008722841600000001,"max_completion_cost":0.051904160000000005,"max_cost":0.052776497400000004},"sats_pricing":{"prompt":0.0000829066485463836,"completion":0.0005481431308851808,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":10.866740238271591,"max_completion_cost":64.66115629173947,"max_cost":65.74789664088547},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.7-flash-20260119","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","created":1768409315,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.7700000000000001,"max_completion_cost":1.9712000000000003,"max_cost":2.4948000000000006},"sats_pricing":{"prompt":0.002398126197622666,"completion":0.01918500958098133,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002398126197622666,"input_cache_write":0.0,"max_prompt_cost":959.2504790490665,"max_completion_cost":2455.68122636561,"max_cost":3107.9715521189755},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-codex-20260114","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","created":1766505011,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.01081344,"max_cost":0.02973696},"sats_pricing":{"prompt":0.0001027768370409714,"completion":0.0004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":26.942331169268407,"max_completion_cost":13.471165584634203,"max_cost":37.045705357744055},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-1.6-flash-20250625","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"seed-1.6","name":"ByteDance Seed: Seed 1.6","created":1766504997,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0720896,"max_completion_cost":0.0720896,"max_cost":0.135168},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":89.80777056422802,"max_completion_cost":89.80777056422802,"max_cost":168.38956980792756},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-1.6-20250625","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"minimax-m2.1","name":"MiniMax: MiniMax M2.1","created":1766454997,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":4.125e-7,"max_prompt_cost":0.067584,"max_completion_cost":0.17301504,"max_cost":0.19734528},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.000513884185204857,"max_prompt_cost":84.19478490396378,"max_completion_cost":215.53864935414725,"max_cost":245.8487719195742},"per_request_limits":null,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2.1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"glm-4.7","name":"Z.ai: GLM 4.7","created":1766378014,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.21e-7,"input_cache_write":0.0,"max_prompt_cost":0.13381632000000002,"max_completion_cost":0.31719424,"max_cost":0.36450304},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.003014787219868494,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00015073936099342474,"input_cache_write":0.0,"max_prompt_cost":166.70567410984827,"max_completion_cost":395.15419048260327,"max_cost":454.0905399153779},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.7-20251222","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.3e-6,"request":0.0,"image":5.5e-7,"web_search":0.015400000000000002,"internal_reasoning":3.3e-6,"input_cache_read":5.5e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.5767168,"max_completion_cost":0.2162688,"max_cost":0.7569408000000001},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.004111073481638856,"request":0.001,"image":0.000685178913606476,"web_search":19.18500958098133,"internal_reasoning":0.004111073481638856,"input_cache_read":0.0000685178913606476,"input_cache_write":0.00011419648560107929,"max_prompt_cost":718.4621645138242,"max_completion_cost":269.4233116926841,"max_cost":942.9815909243943},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-flash-preview-20251217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"}},{"id":"gemini-3-flash-preview:batch","name":"Google: Gemini 3 Flash Preview (batch)","created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.65e-6,"request":0.0,"image":2.75e-7,"web_search":0.015400000000000002,"internal_reasoning":1.65e-6,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2883584,"max_completion_cost":0.1081344,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.002055536740819428,"request":0.001,"image":0.000342589456803238,"web_search":19.18500958098133,"internal_reasoning":0.002055536740819428,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":359.2310822569121,"max_completion_cost":134.71165584634204,"max_cost":471.4907954621971},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-flash-preview-20251217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"}},{"id":"nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","created":1765731275,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":2.64e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.32e-8,"input_cache_write":0.0,"max_prompt_cost":0.017301504,"max_completion_cost":0.062285256,"max_cost":0.064015446},"sats_pricing":{"prompt":0.00008222146963277711,"completion":0.00032888587853110844,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000016444293926555425,"input_cache_write":0.0,"max_prompt_cost":21.553864935414722,"max_completion_cost":77.59371643596589,"max_cost":79.74915226238915},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3-nano-30b-a3b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","created":1765389783,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.24640000000000004,"max_completion_cost":0.49280000000000007,"max_cost":0.6776000000000001},"sats_pricing":{"prompt":0.002398126197622666,"completion":0.01918500958098133,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002398126197622666,"input_cache_write":0.0,"max_prompt_cost":306.9601532957013,"max_completion_cost":613.9203065914026,"max_cost":844.1404215631785},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":32000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-chat-20251211","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000231,"completion":0.0001848,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.24,"max_completion_cost":23.6544,"max_cost":29.9376},"sats_pricing":{"prompt":0.02877751437147199,"completion":0.2302201149717759,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":11511.005748588796,"max_completion_cost":29468.174716387315,"max_cost":37295.6586254277},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-pro-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"}},{"id":"gpt-5.2-pro:batch","name":"OpenAI: GPT-5.2 Pro (batch)","created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.00001155,"completion":0.0000924,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.62,"max_completion_cost":11.8272,"max_cost":14.9688},"sats_pricing":{"prompt":0.014388757185735995,"completion":0.11511005748588796,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5755.502874294398,"max_completion_cost":14734.087358193658,"max_cost":18647.82931271385},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-pro-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"}},{"id":"gpt-5.2","name":"OpenAI: GPT-5.2","created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.7700000000000001,"max_completion_cost":1.9712000000000003,"max_cost":2.4948000000000006},"sats_pricing":{"prompt":0.002398126197622666,"completion":0.01918500958098133,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002398126197622666,"input_cache_write":0.0,"max_prompt_cost":959.2504790490665,"max_completion_cost":2455.68122636561,"max_cost":3107.9715521189755},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.2:batch","name":"OpenAI: GPT-5.2 (batch)","created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":9.625e-7,"completion":7.7e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":9.625e-8,"input_cache_write":0.0,"max_prompt_cost":0.38500000000000006,"max_completion_cost":0.9856000000000001,"max_cost":1.2474000000000003},"sats_pricing":{"prompt":0.001199063098811333,"completion":0.009592504790490664,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001199063098811333,"input_cache_write":0.0,"max_prompt_cost":479.62523952453324,"max_completion_cost":1227.840613182805,"max_cost":1553.9857760594878},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"devstral-2512","name":"Mistral: Devstral 2 2512","created":1765285419,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","context_length":262144,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.11534336,"max_completion_cost":0.46137300000000003,"max_cost":0.48444176000000005},"sats_pricing":{"prompt":0.0005481431308851808,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000054814313088518084,"input_cache_write":0.0,"max_prompt_cost":143.69243290276484,"max_completion_cost":574.7691834679284,"max_cost":603.5077796771076},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/devstral-2512","alias_ids":null,"forwarded_model_id":null},{"id":"relace-search","name":"Relace: Relace Search","created":1765213560,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":3.3e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":0.4224,"max_cost":0.5632},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":350.8116037665157,"max_completion_cost":526.2174056497736,"max_cost":701.6232075330314},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"relace/relace-search-20251208","alias_ids":null,"forwarded_model_id":null},{"id":"glm-4.6v","name":"Z.ai: GLM 4.6V","created":1765207462,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","context_length":131072,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.05e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.03244032,"max_cost":0.06488064},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0012333220444916567,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00007536968049671237,"input_cache_write":0.0,"max_prompt_cost":53.88466233853681,"max_completion_cost":40.413496753902606,"max_cost":80.82699350780521},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.6-20251208","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","created":1764878934,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":0.55,"max_completion_cost":1.4080000000000001,"max_cost":1.7820000000000003},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000171294728401619,"input_cache_write":0.0,"max_prompt_cost":685.178913606476,"max_completion_cost":1754.0580188325787,"max_cost":2219.979680084982},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-codex-max-20251204","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"nova-2-lite-v1","name":"Amazon: Nova 2 Lite","created":1764696672,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","context_length":1000000,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.18022125000000003,"max_cost":0.48859470000000005},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":411.1073481638856,"max_completion_cost":224.51600051600204,"max_cost":608.6814286179674},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65535,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-2-lite-v1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","created":1764681735,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.0461373,"max_cost":0.05767168},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027407156544259042,"input_cache_write":0.0,"max_prompt_cost":71.84621645138242,"max_completion_cost":57.47691834679284,"max_cost":71.84621645138242},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/ministral-14b-2512","alias_ids":null,"forwarded_model_id":null},{"id":"ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.65e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.034602975,"max_cost":0.04325376},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0002055536740819428,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000020555367408194277,"input_cache_write":0.0,"max_prompt_cost":53.88466233853681,"max_completion_cost":43.10768876009463,"max_cost":53.88466233853681},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/ministral-8b-2512","alias_ids":null,"forwarded_model_id":null},{"id":"ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","created":1764681560,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":1.1e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.01441792,"max_completion_cost":0.011534270000000001,"max_cost":0.01441792},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.0,"max_prompt_cost":17.961554112845604,"max_completion_cost":14.369161068806852,"max_cost":17.961554112845604},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/ministral-3b-2512","alias_ids":null,"forwarded_model_id":null},{"id":"mistral-large-2512","name":"Mistral: Mistral Large 3 2512","created":1764624472,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.34602975,"max_cost":0.3748657},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.002055536740819428,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0,"max_prompt_cost":179.61554112845604,"max_completion_cost":431.07688760094635,"max_cost":467.0001328624203},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large-2512","alias_ids":null,"forwarded_model_id":null},{"id":"deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","created":1764594642,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":2.8600000000000005e-7,"completion":4.1800000000000006e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.4300000000000002e-7,"input_cache_write":0.0,"max_prompt_cost":0.04685824000000001,"max_completion_cost":0.06163660800000001,"max_cost":0.06632243200000001},"sats_pricing":{"prompt":0.00035629303507536756,"completion":0.0005207359743409218,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00017814651753768378,"input_cache_write":0.0,"max_prompt_cost":58.375050866748225,"max_completion_cost":76.78564383241496,"max_cost":82.6231489190898},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v3.2-20251201","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false}},{"id":"claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":1.1,"max_completion_cost":1.7600000000000002,"max_cost":2.5080000000000005},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.0342589456803238,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.00856473642008095,"max_prompt_cost":1370.357827212952,"max_completion_cost":2192.5725235407235,"max_cost":3124.415846045531},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-opus-20251124","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"claude-opus-4.5:batch","name":"Anthropic: Claude Opus 4.5 (batch)","created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":0.55,"max_completion_cost":0.8800000000000001,"max_cost":1.2540000000000002},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.0171294728401619,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.004282368210040475,"max_prompt_cost":685.178913606476,"max_completion_cost":1096.2862617703618,"max_cost":1562.2079230227655},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-opus-20251124","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gemini-3-pro-image-preview","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","created":1763653797,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":2.2e-6,"web_search":0.015400000000000002,"internal_reasoning":0.0000132,"input_cache_read":2.2e-7,"input_cache_write":4.125e-7,"max_prompt_cost":0.1441792,"max_completion_cost":0.4325376,"max_cost":0.5046272},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.016444293926555425,"request":0.001,"image":0.002740715654425904,"web_search":19.18500958098133,"internal_reasoning":0.016444293926555425,"input_cache_read":0.0002740715654425904,"input_cache_write":0.000513884185204857,"max_prompt_cost":179.61554112845604,"max_completion_cost":538.8466233853682,"max_cost":628.6543939495962},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-pro-image-preview-20251120","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gpt-5.1","name":"OpenAI: GPT-5.1","created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":0.55,"max_completion_cost":1.4080000000000001,"max_cost":1.7820000000000003},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000171294728401619,"input_cache_write":0.0,"max_prompt_cost":685.178913606476,"max_completion_cost":1754.0580188325787,"max_cost":2219.979680084982},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.1:batch","name":"OpenAI: GPT-5.1 (batch)","created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.875000000000001e-7,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":6.875e-8,"input_cache_write":0.0,"max_prompt_cost":0.275,"max_completion_cost":0.7040000000000001,"max_cost":0.8910000000000001},"sats_pricing":{"prompt":0.0008564736420080951,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000856473642008095,"input_cache_write":0.0,"max_prompt_cost":342.589456803238,"max_completion_cost":877.0290094162893,"max_cost":1109.989840042491},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"}},{"id":"gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","created":1763060298,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.4300000000000002e-7,"input_cache_write":0.0,"max_prompt_cost":0.55,"max_completion_cost":1.4080000000000001,"max_cost":1.7820000000000003},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.00017814651753768378,"input_cache_write":0.0,"max_prompt_cost":685.178913606476,"max_completion_cost":1754.0580188325787,"max_cost":2219.979680084982},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-codex-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","created":1763057820,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.11,"max_completion_cost":0.2816,"max_cost":0.35640000000000005},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":137.0357827212952,"max_completion_cost":350.8116037665157,"max_cost":443.9959360169965},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-codex-mini-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","created":1762440622,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.270336,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":215.53864935414725,"max_completion_cost":336.7791396158551,"max_cost":471.4907954621971},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2-thinking-20251106","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true}},{"id":"nova-premier-v1","name":"Amazon: Nova Premier 1.0","created":1761950332,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.875000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":2.7500000000000004,"max_completion_cost":0.44000000000000006,"max_cost":3.1020000000000003},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.0171294728401619,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0008564736420080951,"input_cache_write":0.0,"max_prompt_cost":3425.8945680323804,"max_completion_cost":548.1431308851809,"max_cost":3864.4090727405246},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-premier-v1","alias_ids":null,"forwarded_model_id":null},{"id":"sonar-pro-search","name":"Perplexity: Sonar Pro Search","created":1761854366,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.0198,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.66,"max_completion_cost":0.132,"max_cost":0.7656000000000001},"sats_pricing":{"prompt":0.004111073481638856,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":24.666440889833137,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":822.2146963277712,"max_completion_cost":164.44293926555423,"max_cost":953.7690477402147},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-pro-search","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","created":1761835144,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","context_length":32768,"architecture":{"modality":"text+file+audio->text","input_modalities":["text","audio","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":3.3e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.00360448,"max_completion_cost":0.008650620000000001,"max_cost":0.009371560000000001},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013703578272129521,"input_cache_write":0.0,"max_prompt_cost":4.490388528211401,"max_completion_cost":10.776768024768097,"max_cost":11.674900544723466},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/voxtral-small-24b-2507","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","created":1761752836,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.01081344,"max_completion_cost":0.02162688,"max_cost":0.0270336},"sats_pricing":{"prompt":0.0001027768370409714,"completion":0.0004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000513884185204857,"input_cache_write":0.0,"max_prompt_cost":13.471165584634203,"max_completion_cost":26.942331169268407,"max_cost":33.67791396158551},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-safeguard-20b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"minimax-m2","name":"MiniMax: MiniMax M2","created":1761252093,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.805e-7,"completion":1.122e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":4.125e-7,"max_prompt_cost":0.0574464,"max_completion_cost":0.147062784,"max_cost":0.167743488},"sats_pricing":{"prompt":0.00034944124593930275,"completion":0.001397764983757211,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.000513884185204857,"max_prompt_cost":71.5655671683692,"max_completion_cost":183.20785195102516,"max_cost":208.97145613163806},"per_request_limits":null,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","created":1760624583,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["file","image","text"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":0.2816,"max_cost":1.0296},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":1370.357827212952,"max_completion_cost":350.8116037665157,"max_cost":1282.6549262713231},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-image-mini","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":0.22,"max_completion_cost":0.35200000000000004,"max_cost":0.5016},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0017129472840161902,"max_prompt_cost":274.0715654425904,"max_completion_cost":438.51450470814467,"max_cost":624.8831692091061},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-haiku-20251001","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"claude-haiku-4.5:batch","name":"Anthropic: Claude Haiku 4.5 (batch)","created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":6.875000000000001e-7,"max_prompt_cost":0.11,"max_completion_cost":0.17600000000000002,"max_cost":0.2508},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0008564736420080951,"max_prompt_cost":137.0357827212952,"max_completion_cost":219.25725235407234,"max_cost":312.44158460455304},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-haiku-20251001","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","created":1760463308,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":8.25e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.32e-7,"input_cache_write":0.0,"max_prompt_cost":0.0720896,"max_completion_cost":0.194641425,"max_cost":0.20185055000000002},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.001027768370409714,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00016444293926555422,"input_cache_write":0.0,"max_prompt_cost":89.80777056422802,"max_completion_cost":242.4803638623934,"max_cost":251.4613464724903},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-8b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-5-image","name":"OpenAI: GPT-5 Image","created":1760447986,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.3750000000000002e-6,"input_cache_write":0.0,"max_prompt_cost":4.4,"max_completion_cost":1.4080000000000001,"max_cost":4.4},"sats_pricing":{"prompt":0.013703578272129521,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0017129472840161902,"input_cache_write":0.0,"max_prompt_cost":5481.431308851808,"max_completion_cost":1754.0580188325787,"max_cost":5481.431308851808},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-image","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gemini-2.5-flash-image","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","created":1759870431,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","context_length":32768,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":3.3e-7,"web_search":0.015400000000000002,"internal_reasoning":2.7500000000000004e-6,"input_cache_read":3.3e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.01081344,"max_completion_cost":0.022528000000000003,"max_cost":0.030638080000000005},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0034258945680323803,"request":0.001,"image":0.0004111073481638856,"web_search":19.18500958098133,"internal_reasoning":0.0034258945680323803,"input_cache_read":0.000041110734816388555,"input_cache_write":0.00011419648560107929,"max_prompt_cost":13.471165584634203,"max_completion_cost":28.06492830132126,"max_cost":38.168302489796915},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-flash-image","alias_ids":null,"forwarded_model_id":null},{"id":"qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","created":1759794479,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.19e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.083623936,"max_completion_cost":0.2595219,"max_cost":0.267884485},"sats_pricing":{"prompt":0.00039740376989175604,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":104.1770138545045,"max_completion_cost":323.30715181652454,"max_cost":333.7250916442369},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-30b-a3b-thinking","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","created":1759794476,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.01081344,"max_cost":0.05136384},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":53.88466233853681,"max_completion_cost":13.471165584634203,"max_cost":63.98803652701246},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-30b-a3b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-5-pro","name":"OpenAI: GPT-5 Pro","created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000165,"completion":0.000132,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.6000000000000005,"max_completion_cost":16.896,"max_cost":21.384},"sats_pricing":{"prompt":0.020555367408194282,"completion":0.16444293926555426,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":8222.146963277712,"max_completion_cost":21048.69622599094,"max_cost":26639.756161019784},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-pro-2025-10-06","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high"],"default_effort":"high"}},{"id":"gpt-5-pro:batch","name":"OpenAI: GPT-5 Pro (batch)","created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-6,"completion":0.000066,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.3000000000000003,"max_completion_cost":8.448,"max_cost":10.692},"sats_pricing":{"prompt":0.010277683704097141,"completion":0.08222146963277713,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4111.073481638856,"max_completion_cost":10524.34811299547,"max_cost":13319.878080509892},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-pro-2025-10-06","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high"],"default_effort":"high"}},{"id":"glm-4.6","name":"Z.ai: GLM 4.6","created":1759235576,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.1115136,"max_completion_cost":0.2883584,"max_cost":0.32778240000000003},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":138.9213950915402,"max_completion_cost":359.2310822569121,"max_cost":408.3447067842243},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.6","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":4.125e-6,"max_prompt_cost":3.3000000000000003,"max_completion_cost":1.056,"max_cost":4.1448},"sats_pricing":{"prompt":0.004111073481638856,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0004111073481638856,"input_cache_write":0.0051388418520485705,"max_prompt_cost":4111.073481638856,"max_completion_cost":1315.5435141244338,"max_cost":5163.5082929384025},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"claude-sonnet-4.5:batch","name":"Anthropic: Claude Sonnet 4.5 (batch)","created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":2.0625e-6,"max_prompt_cost":1.6500000000000001,"max_completion_cost":0.528,"max_cost":2.0724},"sats_pricing":{"prompt":0.002055536740819428,"completion":0.010277683704097141,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0025694209260242852,"max_prompt_cost":2055.536740819428,"max_completion_cost":657.7717570622169,"max_cost":2581.7541464692013},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","created":1759150481,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":2.97e-7,"completion":4.51e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.048660480000000006,"max_completion_cost":0.066502656,"max_cost":0.07136870399999999},"sats_pricing":{"prompt":0.00036999661334749707,"completion":0.0005618467091573103,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":60.62024513085392,"max_completion_cost":82.84766834550034,"max_cost":88.90969285858573},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v3.2-exp","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","created":1758931878,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.0648802,"max_cost":0.06920584},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002055536740819428,"input_cache_write":0.0,"max_prompt_cost":53.88466233853681,"max_completion_cost":80.82644536467433,"max_cost":86.21524048440655},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thedrummer/cydonia-24b-v4.1","alias_ids":null,"forwarded_model_id":null},{"id":"relace-apply-3","name":"Relace: Relace Apply 3","created":1758891572,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9.35e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.23936000000000002,"max_completion_cost":0.17600000000000002,"max_cost":0.29568000000000005},"sats_pricing":{"prompt":0.0011648041531310091,"completion":0.0017129472840161902,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":298.18986320153834,"max_completion_cost":219.25725235407234,"max_cost":368.35218395484156},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"relace/relace-apply-3","alias_ids":null,"forwarded_model_id":null},{"id":"qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","created":1758668687,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.3100000000000002e-7,"completion":2.0900000000000003e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.030277632000000002,"max_completion_cost":0.06848512000000001,"max_cost":0.09119334400000001},"sats_pricing":{"prompt":0.0002877751437147199,"completion":0.002603679871704609,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":37.71926363697577,"max_completion_cost":85.31738203601662,"max_cost":113.60682976374845},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-235b-a22b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","created":1758548275,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":2.97e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.048660480000000006,"max_completion_cost":0.1622016,"max_cost":0.167067648},"sats_pricing":{"prompt":0.00036999661334749707,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":60.62024513085392,"max_completion_cost":202.06748376951305,"max_cost":208.12950828259844},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v3.1-terminus","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","created":1758115536,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.1450000000000002e-7,"completion":1.0725000000000001e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.29e-8,"input_cache_write":2.6812500000000003e-7,"max_prompt_cost":0.21450000000000002,"max_completion_cost":0.07028736000000001,"max_cost":0.27072988800000003},"sats_pricing":{"prompt":0.00026721977630652565,"completion":0.0013360988815326283,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000053443955261305126,"input_cache_write":0.0003340247203831571,"max_prompt_cost":267.21977630652566,"max_completion_cost":87.56257630012233,"max_cost":337.2698373466235},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-flash","alias_ids":null,"forwarded_model_id":null},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","created":1757612213,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":9.900000000000001e-8,"completion":1.21e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.025952256000000003,"max_completion_cost":0.01982464,"max_cost":0.04415488000000001},"sats_pricing":{"prompt":0.0001233322044491657,"completion":0.001507393609934247,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":32.33079740312209,"max_completion_cost":24.697136905162704,"max_cost":55.007259470589666},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-next-80b-a3b-instruct-2509","alias_ids":null,"forwarded_model_id":null},{"id":"kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","created":1757021147,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.270336,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.0034258945680323803,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":215.53864935414725,"max_completion_cost":336.7791396158551,"max_cost":471.4907954621971},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2-0905","alias_ids":null,"forwarded_model_id":null},{"id":"hermes-4-405b","name":"Nous: Hermes 4 405B","created":1756235463,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":3.3e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.3892812,"max_cost":0.4037},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":179.61554112845604,"max_completion_cost":484.95867218804597,"max_cost":502.9213225871534},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nousresearch/hermes-4-405b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","created":1755779628,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":2.75e-7,"completion":1.0450000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.4300000000000002e-7,"input_cache_write":0.0,"max_prompt_cost":0.045056,"max_completion_cost":0.15409152000000004,"max_cost":0.15859712000000004},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.0013018399358523045,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00017814651753768378,"input_cache_write":0.0,"max_prompt_cost":56.12985660264251,"max_completion_cost":191.96410958103743,"max_cost":197.5770952413017},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-chat-v3.1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","created":1755095639,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.2306854,"max_cost":0.24222000000000002},"sats_pricing":{"prompt":0.0005481431308851808,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000054814313088518084,"input_cache_write":0.0,"max_prompt_cost":71.84621645138242,"max_completion_cost":287.383221376137,"max_cost":301.752793552292},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3.1","alias_ids":null,"forwarded_model_id":null},{"id":"glm-4.5v","name":"Z.ai: GLM 4.5V","created":1754922288,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","context_length":65536,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":1.98e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.21e-7,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.03244032,"max_cost":0.06488064},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.0024666440889833134,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00015073936099342474,"input_cache_write":0.0,"max_prompt_cost":53.88466233853681,"max_completion_cost":40.413496753902606,"max_cost":80.82699350780521},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.5v","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gpt-5","name":"OpenAI: GPT-5","created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":0.55,"max_completion_cost":1.4080000000000001,"max_cost":1.7820000000000003},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000171294728401619,"input_cache_write":0.0,"max_prompt_cost":685.178913606476,"max_completion_cost":1754.0580188325787,"max_cost":2219.979680084982},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gpt-5:batch","name":"OpenAI: GPT-5 (batch)","created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.875000000000001e-7,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":6.875e-8,"input_cache_write":0.0,"max_prompt_cost":0.275,"max_completion_cost":0.7040000000000001,"max_cost":0.8910000000000001},"sats_pricing":{"prompt":0.0008564736420080951,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000856473642008095,"input_cache_write":0.0,"max_prompt_cost":342.589456803238,"max_completion_cost":877.0290094162893,"max_cost":1109.989840042491},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gpt-5-mini","name":"OpenAI: GPT-5 Mini","created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.11,"max_completion_cost":0.2816,"max_cost":0.35640000000000005},"sats_pricing":{"prompt":0.000342589456803238,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000342589456803238,"input_cache_write":0.0,"max_prompt_cost":137.0357827212952,"max_completion_cost":350.8116037665157,"max_cost":443.9959360169965},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-mini-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gpt-5-mini:batch","name":"OpenAI: GPT-5 Mini (batch)","created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.375e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-8,"input_cache_write":0.0,"max_prompt_cost":0.055,"max_completion_cost":0.1408,"max_cost":0.17820000000000003},"sats_pricing":{"prompt":0.000171294728401619,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000171294728401619,"input_cache_write":0.0,"max_prompt_cost":68.5178913606476,"max_completion_cost":175.40580188325785,"max_cost":221.99796800849825},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-mini-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gpt-5-nano","name":"OpenAI: GPT-5 Nano","created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":4.4e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":0.0,"max_prompt_cost":0.022000000000000002,"max_completion_cost":0.05632,"max_cost":0.07128000000000001},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.0005481431308851808,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":6.8517891360647605e-6,"input_cache_write":0.0,"max_prompt_cost":27.407156544259042,"max_completion_cost":70.16232075330313,"max_cost":88.7991872033993},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-nano-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gpt-5-nano:batch","name":"OpenAI: GPT-5 Nano (batch)","created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.75e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.7500000000000002e-9,"input_cache_write":0.0,"max_prompt_cost":0.011000000000000001,"max_completion_cost":0.02816,"max_cost":0.035640000000000005},"sats_pricing":{"prompt":0.0000342589456803238,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":3.4258945680323803e-6,"input_cache_write":0.0,"max_prompt_cost":13.703578272129521,"max_completion_cost":35.08116037665157,"max_cost":44.39959360169965},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-nano-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"}},{"id":"gpt-oss-120b","name":"OpenAI: gpt-oss-120b","created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.04325376,"max_cost":0.0540672},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001027768370409714,"input_cache_write":0.0,"max_prompt_cost":26.942331169268407,"max_completion_cost":53.88466233853681,"max_cost":67.35582792317102},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-120b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"gpt-oss-120b:batch","name":"OpenAI: gpt-oss-120b (batch)","created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.256e-8,"completion":1.4960000000000002e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00426770432,"max_completion_cost":0.017647414400000002,"max_cost":0.018074210880000004},"sats_pricing":{"prompt":0.00004056259168550338,"completion":0.0001863686645009615,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.316620017402299,"max_completion_cost":21.98479313919142,"max_cost":22.516487591005},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-120b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"gpt-oss-20b","name":"OpenAI: gpt-oss-20b","created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.3e-8,"completion":1.4300000000000002e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.004325376,"max_completion_cost":0.016868852000000004,"max_cost":0.017301416000000003},"sats_pricing":{"prompt":0.000041110734816388555,"completion":0.00017814651753768378,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":5.388466233853681,"max_completion_cost":21.01487579481533,"max_cost":21.553755306788553},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-20b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"gpt-oss-20b:batch","name":"OpenAI: gpt-oss-20b (batch)","created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.64e-8,"completion":1.2320000000000002e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0034603008,"max_completion_cost":0.014533164800000001,"max_cost":0.014879216},"sats_pricing":{"prompt":0.00003288858785311085,"completion":0.00015348007664785064,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.310772987082945,"max_completion_cost":18.10512376168705,"max_cost":18.53622737126563},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-20b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":0.0000165,"completion":0.0000825,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.65e-6,"input_cache_write":0.000020625,"max_prompt_cost":3.3000000000000003,"max_completion_cost":2.64,"max_cost":5.412000000000001},"sats_pricing":{"prompt":0.020555367408194282,"completion":0.10277683704097139,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.002055536740819428,"input_cache_write":0.025694209260242847,"max_prompt_cost":4111.073481638856,"max_completion_cost":3288.858785311085,"max_cost":6742.160509887724},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.1-opus-20250805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"claude-opus-4.1:batch","name":"Anthropic: Claude Opus 4.1 (batch)","created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":8.25e-6,"completion":0.00004125,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":8.25e-7,"input_cache_write":0.0000103125,"max_prompt_cost":1.6500000000000001,"max_completion_cost":1.32,"max_cost":2.7060000000000004},"sats_pricing":{"prompt":0.010277683704097141,"completion":0.051388418520485694,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.001027768370409714,"input_cache_write":0.012847104630121424,"max_prompt_cost":2055.536740819428,"max_completion_cost":1644.4293926555424,"max_cost":3371.080254943862},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.1-opus-20250805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"codestral-2508","name":"Mistral: Codestral 2508","created":1754079630,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","context_length":256000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.08448,"max_completion_cost":0.20275200000000002,"max_cost":0.219648},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0012333220444916567,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":105.2434811299547,"max_completion_cost":252.5843547118913,"max_cost":273.6330509378823},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":204800,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/codestral-2508","alias_ids":null,"forwarded_model_id":null},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","created":1753972379,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.15571314,"max_cost":0.160038615},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":53.88466233853681,"max_completion_cost":193.9842910899147,"max_cost":199.37288065597284},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-30b-a3b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","created":1753806965,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":3.3e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.07785657,"max_cost":0.08074022},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":35.92310822569121,"max_completion_cost":96.99214554495735,"max_cost":100.58453858899611},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-30b-a3b-instruct-2507","alias_ids":null,"forwarded_model_id":null},{"id":"glm-4.5","name":"Z.ai: GLM 4.5","created":1753471347,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.21e-7,"input_cache_write":0.0,"max_prompt_cost":0.08650752,"max_completion_cost":0.23789568,"max_cost":0.25952256},"sats_pricing":{"prompt":0.0008222146963277712,"completion":0.003014787219868494,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00015073936099342474,"input_cache_write":0.0,"max_prompt_cost":107.76932467707363,"max_completion_cost":296.36564286195244,"max_cost":323.30797403122085},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.5","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"glm-4.5-air","name":"Z.ai: GLM 4.5 Air","created":1753471258,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.4300000000000002e-7,"completion":9.35e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.018743296000000003,"max_completion_cost":0.09191424000000001,"max_cost":0.09660006400000001},"sats_pricing":{"prompt":0.00017814651753768378,"completion":0.0011648041531310091,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000342589456803238,"input_cache_write":0.0,"max_prompt_cost":23.35002034669929,"max_completion_cost":114.50490746939073,"max_cost":120.34241255606555},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.5-air","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","created":1753449557,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":4.95e-7,"completion":3.85e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.06336,"max_completion_cost":0.0630784,"max_cost":0.11832832000000001},"sats_pricing":{"prompt":0.0006166610222458283,"completion":0.004796252395245332,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":78.93261084746602,"max_completion_cost":78.58179924369952,"max_cost":147.41103590268992},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-235b-a22b-thinking-2507","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","created":1753230546,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.08650752,"max_completion_cost":0.0720896,"max_cost":0.13697024000000002},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":107.76932467707363,"max_completion_cost":89.80777056422802,"max_cost":170.63476407203325},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-480b-a35b-07-25","alias_ids":null,"forwarded_model_id":null},{"id":"ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","created":1753205056,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.01408,"max_completion_cost":0.00045056,"max_cost":0.01430528},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":17.540580188325784,"max_completion_cost":0.5612985660264251,"max_cost":17.821229471339},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":2048,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance/ui-tars-1.5-7b","alias_ids":null,"forwarded_model_id":null},{"id":"gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","created":1753200276,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":4.4e-7,"request":0.0,"image":1.1e-7,"web_search":0.015400000000000002,"internal_reasoning":4.4e-7,"input_cache_read":1.1000000000000001e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.11534336,"max_completion_cost":0.0288354,"max_cost":0.13696991},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0005481431308851808,"request":0.001,"image":0.0001370357827212952,"web_search":19.18500958098133,"internal_reasoning":0.0005481431308851808,"input_cache_read":0.000013703578272129521,"input_cache_write":0.00011419648560107929,"max_prompt_cost":143.69243290276484,"max_completion_cost":35.922560082560324,"max_cost":170.63435296468506},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-flash-lite","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","created":1753119555,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.5400000000000003e-7,"completion":8.8e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.020185088000000004,"max_completion_cost":0.10380832000000001,"max_cost":0.10582695200000002},"sats_pricing":{"prompt":0.0001918500958098133,"completion":0.0010962862617703616,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0,"max_prompt_cost":25.146175757983848,"max_completion_cost":129.32231258347895,"max_cost":131.83708363935398},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-235b-a22b-07-25","alias_ids":null,"forwarded_model_id":null},{"id":"kimi-k2","name":"MoonshotAI: Kimi K2 0711","created":1752263252,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.270000000000001e-7,"completion":2.5300000000000003e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.08218214400000001,"max_completion_cost":0.24870912000000003,"max_cost":0.26925465600000004},"sats_pricing":{"prompt":0.0007811039615113827,"completion":0.0031518230025897897,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":102.38085844321995,"max_completion_cost":309.8368084465867,"max_cost":335.4320230573917},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2","alias_ids":null,"forwarded_model_id":null},{"id":"dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","created":1752094966,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02816,"max_completion_cost":0.00811008,"max_cost":0.03446784},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0012333220444916567,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":35.08116037665157,"max_completion_cost":10.103374188475652,"max_cost":42.93934030102152},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"venice/uncensored","alias_ids":null,"forwarded_model_id":null},{"id":"hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","created":1751987664,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5400000000000003e-7,"completion":6.270000000000001e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.020185088000000004,"max_completion_cost":0.07396342800000001,"max_cost":0.07598206000000002},"sats_pricing":{"prompt":0.0001918500958098133,"completion":0.0007811039615113827,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":25.146175757983848,"max_completion_cost":92.14214771572875,"max_cost":94.65691877160378},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hunyuan-a13b-instruct","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"morph-v3-large","name":"Morph: Morph V3 Large","created":1751910858,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9.9e-7,"completion":2.0900000000000003e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.25952256,"max_completion_cost":0.27394048000000004,"max_cost":0.40370176},"sats_pricing":{"prompt":0.0012333220444916567,"completion":0.002603679871704609,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":323.30797403122085,"max_completion_cost":341.2695281440665,"max_cost":502.9235151596769},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"morph/morph-v3-large","alias_ids":null,"forwarded_model_id":null},{"id":"morph-v3-fast","name":"Morph: Morph V3 Fast","created":1751910002,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.23068672,"max_completion_cost":0.17301504,"max_cost":0.2883584},"sats_pricing":{"prompt":0.0010962862617703616,"completion":0.0016444293926555424,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":287.38486580552967,"max_completion_cost":215.53864935414725,"max_cost":359.2310822569121},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"morph/morph-v3-fast","alias_ids":null,"forwarded_model_id":null},{"id":"mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","created":1750443016,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.01056,"max_completion_cost":0.00360448,"max_cost":0.012812800000000001},"sats_pricing":{"prompt":0.0001027768370409714,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.155435141244338,"max_completion_cost":4.490388528211401,"max_cost":15.961927971376465},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-3.2-24b-instruct-2506","alias_ids":null,"forwarded_model_id":null},{"id":"minimax-m1","name":"MiniMax: MiniMax M1","created":1750200414,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.05e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.605,"max_completion_cost":0.09680000000000001,"max_cost":0.6776},"sats_pricing":{"prompt":0.0007536968049671235,"completion":0.003014787219868494,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":753.6968049671235,"max_completion_cost":120.59148879473979,"max_cost":844.1404215631784},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":40000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","created":1750172488,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":3.3e-7,"web_search":0.015400000000000002,"internal_reasoning":2.7500000000000004e-6,"input_cache_read":3.3e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.34603008,"max_completion_cost":0.18022125000000003,"max_cost":0.50462478},"sats_pricing":{"prompt":0.0004111073481638856,"completion":0.0034258945680323803,"request":0.001,"image":0.0004111073481638856,"web_search":19.18500958098133,"internal_reasoning":0.0034258945680323803,"input_cache_read":0.000041110734816388555,"input_cache_write":0.00011419648560107929,"max_prompt_cost":431.0772987082945,"max_completion_cost":224.51600051600204,"max_cost":628.6513791623762},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-flash","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","created":1750169544,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":1.3750000000000002e-6,"web_search":0.015400000000000002,"internal_reasoning":0.000011000000000000001,"input_cache_read":1.375e-7,"input_cache_write":4.125e-7,"max_prompt_cost":1.4417920000000002,"max_completion_cost":0.7208960000000001,"max_cost":2.072576},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.013703578272129521,"request":0.001,"image":0.0017129472840161902,"web_search":19.18500958098133,"internal_reasoning":0.013703578272129521,"input_cache_read":0.000171294728401619,"input_cache_write":0.000513884185204857,"max_prompt_cost":1796.1554112845606,"max_completion_cost":898.0777056422803,"max_cost":2581.9734037215558},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-pro","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"o3-pro","name":"OpenAI: o3 Pro","created":1749598352,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","file","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000022000000000000003,"completion":0.00008800000000000001,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.4,"max_completion_cost":8.8,"max_cost":11.0},"sats_pricing":{"prompt":0.027407156544259043,"completion":0.10962862617703617,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5481.431308851808,"max_completion_cost":10962.862617703617,"max_cost":13703.57827212952},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o3-pro-2025-06-10","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","created":1749137257,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio->text","input_modalities":["file","image","text","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":1.3750000000000002e-6,"web_search":0.015400000000000002,"internal_reasoning":0.000011000000000000001,"input_cache_read":1.375e-7,"input_cache_write":4.125e-7,"max_prompt_cost":1.4417920000000002,"max_completion_cost":0.7208960000000001,"max_cost":2.072576},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.013703578272129521,"request":0.001,"image":0.0017129472840161902,"web_search":19.18500958098133,"internal_reasoning":0.013703578272129521,"input_cache_read":0.000171294728401619,"input_cache_write":0.000513884185204857,"max_prompt_cost":1796.1554112845606,"max_completion_cost":898.0777056422803,"max_cost":2581.9734037215558},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-pro-preview-06-05","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"deepseek-r1-0528","name":"DeepSeek: R1 0528","created":1748455170,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-r1"},"pricing":{"prompt":5.5e-7,"completion":2.3650000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.85e-7,"input_cache_write":0.0,"max_prompt_cost":0.090112,"max_completion_cost":0.07749632000000001,"max_cost":0.14958592},"sats_pricing":{"prompt":0.000685178913606476,"completion":0.002946269328507847,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0004796252395245332,"input_cache_write":0.0,"max_prompt_cost":112.25971320528502,"max_completion_cost":96.54335335654513,"max_cost":186.35112392077315},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-r1-0528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"mistral-medium-3","name":"Mistral: Mistral Medium 3","created":1746627341,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.2306854,"max_cost":0.24222000000000002},"sats_pricing":{"prompt":0.0005481431308851808,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000054814313088518084,"input_cache_write":0.0,"max_prompt_cost":71.84621645138242,"max_completion_cost":287.383221376137,"max_cost":301.752793552292},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3","alias_ids":null,"forwarded_model_id":null},{"id":"llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","created":1745975193,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","context_length":163840,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.9800000000000003e-7,"completion":1.9800000000000003e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.03244032,"max_completion_cost":0.0032440320000000004,"max_cost":0.03244032},"sats_pricing":{"prompt":0.0002466644088983314,"completion":0.0002466644088983314,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":40.413496753902606,"max_completion_cost":4.041349675390261,"max_cost":40.413496753902606},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-guard-4-12b","alias_ids":null,"forwarded_model_id":null},{"id":"qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","created":1745878604,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":1.32e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.005406719999999999,"max_completion_cost":0.0090112,"max_cost":0.012255232000000001},"sats_pricing":{"prompt":0.00016444293926555422,"completion":0.000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.735582792317101,"max_completion_cost":11.225971320528503,"max_cost":15.267320995918764},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-30b-a3b-04-28","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"qwen3-14b","name":"Qwen: Qwen3 14B","created":1745876478,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":1.32e-7,"completion":2.64e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.005406719999999999,"max_completion_cost":0.004325376,"max_cost":0.007569408},"sats_pricing":{"prompt":0.00016444293926555422,"completion":0.00032888587853110844,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.735582792317101,"max_completion_cost":5.388466233853681,"max_cost":9.429815909243942},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-14b-04-28","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"qwen3-32b","name":"Qwen: Qwen3 32B","created":1745875945,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":8.800000000000001e-8,"completion":3.0800000000000006e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00360448,"max_completion_cost":0.005046272000000001,"max_cost":0.007208960000000001},"sats_pricing":{"prompt":0.00010962862617703617,"completion":0.0003837001916196266,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.490388528211401,"max_completion_cost":6.286543939495962,"max_cost":8.980777056422804},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-32b-04-28","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false}},{"id":"o3","name":"OpenAI: o3","created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":8.8e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.44,"max_completion_cost":0.88,"max_cost":1.1},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.010962862617703616,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":548.1431308851808,"max_completion_cost":1096.2862617703615,"max_cost":1370.357827212952},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o3-2025-04-16","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"o3:batch","name":"OpenAI: o3 (batch)","created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.22,"max_completion_cost":0.44,"max_cost":0.55},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.005481431308851808,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":274.0715654425904,"max_completion_cost":548.1431308851808,"max_cost":685.178913606476},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o3-2025-04-16","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"o4-mini:batch","name":"OpenAI: o4 Mini (batch)","created":1744820942,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.05e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.5125e-7,"input_cache_write":0.0,"max_prompt_cost":0.12100000000000001,"max_completion_cost":0.24200000000000002,"max_cost":0.30250000000000005},"sats_pricing":{"prompt":0.0007536968049671235,"completion":0.003014787219868494,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.00018842420124178089,"input_cache_write":0.0,"max_prompt_cost":150.73936099342473,"max_completion_cost":301.47872198684945,"max_cost":376.8484024835618},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o4-mini-2025-04-16","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gpt-4.1","name":"OpenAI: GPT-4.1","created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":8.8e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":2.3046672,"max_completion_cost":0.2883584,"max_cost":2.520936},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.010962862617703616,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000685178913606476,"input_cache_write":0.0,"max_prompt_cost":2871.1079424008703,"max_completion_cost":359.2310822569121,"max_cost":3140.5312540935543},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-2025-04-14","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4.1:batch","name":"OpenAI: GPT-4.1 (batch)","created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":1.1523336,"max_completion_cost":0.1441792,"max_cost":1.260468},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.005481431308851808,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":1435.5539712004352,"max_completion_cost":179.61554112845604,"max_cost":1570.2656270467771},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-2025-04-14","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":1.76e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.46093344,"max_completion_cost":0.05767168,"max_cost":0.5041872000000001},"sats_pricing":{"prompt":0.0005481431308851808,"completion":0.002192572523540723,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":574.2215884801742,"max_completion_cost":71.84621645138242,"max_cost":628.106250818711},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4.1-mini:batch","name":"OpenAI: GPT-4.1 Mini (batch)","created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":8.8e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.23046672,"max_completion_cost":0.02883584,"max_cost":0.25209360000000003},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0010962862617703616,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000685178913606476,"input_cache_write":0.0,"max_prompt_cost":287.1107942400871,"max_completion_cost":35.92310822569121,"max_cost":314.0531254093555},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.11523336,"max_completion_cost":0.41483992000000003,"max_cost":0.4263633},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0005481431308851808,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.000041110734816388555,"input_cache_write":0.0,"max_prompt_cost":143.55539712004355,"max_completion_cost":516.7992103749044,"max_cost":531.1548049012218},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":942818,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4.1-nano:batch","name":"OpenAI: GPT-4.1 Nano (batch)","created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-8,"input_cache_write":0.0,"max_prompt_cost":0.05761668,"max_completion_cost":0.00720896,"max_cost":0.06302340000000001},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000171294728401619,"input_cache_write":0.0,"max_prompt_cost":71.77769856002178,"max_completion_cost":8.980777056422802,"max_cost":78.51328135233888},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","alias_ids":null,"forwarded_model_id":null},{"id":"llama-4-maverick","name":"Meta: Llama 4 Maverick","created":1743881822,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","context_length":524288,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":3.85e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.87e-7,"input_cache_write":0.0,"max_prompt_cost":0.20185088,"max_completion_cost":0.0360448,"max_cost":0.22528000000000004},"sats_pricing":{"prompt":0.0004796252395245332,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00023296083062620182,"input_cache_write":0.0,"max_prompt_cost":251.46175757983846,"max_completion_cost":44.90388528211401,"max_cost":280.6492830132126},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-4-maverick-17b-128e-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"llama-4-scout","name":"Meta: Llama 4 Scout","created":1743881519,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","context_length":1310720,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":3.3e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0360448,"max_completion_cost":0.00540672,"max_cost":0.03964928000000001},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0004111073481638856,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":44.90388528211401,"max_completion_cost":6.735582792317102,"max_cost":49.39427381032542},"per_request_limits":null,"top_provider":{"context_length":327680,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-4-scout-17b-16e-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","created":1742824755,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":3.19e-7,"completion":1.2540000000000002e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.21e-7,"input_cache_write":0.0,"max_prompt_cost":0.040832,"max_completion_cost":0.14446080000000003,"max_cost":0.14854400000000004},"sats_pricing":{"prompt":0.00039740376989175604,"completion":0.0015622079230227653,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00015073936099342474,"input_cache_write":0.0,"max_prompt_cost":50.86768254614478,"max_completion_cost":179.9663527322226,"max_cost":185.0531209868371},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-chat-v3-0324","alias_ids":null,"forwarded_model_id":null},{"id":"mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","created":1742238937,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3.8610000000000005e-7,"completion":6.105e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.04942080000000001,"max_completion_cost":0.0625152,"max_cost":0.07239936000000001},"sats_pricing":{"prompt":0.0004809955973517462,"completion":0.0007605485941031883,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":61.56743646102351,"max_completion_cost":77.88017603616649,"max_cost":90.1936633283712},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-3.1-24b-instruct-2503","alias_ids":null,"forwarded_model_id":null},{"id":"gemma-3-4b-it","name":"Google: Gemma 3 4B","created":1741905510,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":5.5e-8,"completion":1.1e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.00180224,"max_cost":0.00811008},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.0001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":8.980777056422802,"max_completion_cost":2.2451942641057006,"max_cost":10.103374188475652},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-3-4b-it","alias_ids":null,"forwarded_model_id":null},{"id":"gemma-3-12b-it","name":"Google: Gemma 3 12B","created":1741902625,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":5.5e-8,"completion":1.65e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.00270336,"max_cost":0.0090112},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.0002055536740819428,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":8.980777056422802,"max_completion_cost":3.367791396158551,"max_cost":11.225971320528503},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-3-12b-it","alias_ids":null,"forwarded_model_id":null},{"id":"command-a","name":"Cohere: Command A","created":1741894342,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.7040000000000001,"max_completion_cost":0.09011200000000001,"max_cost":0.771584},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":877.0290094162893,"max_completion_cost":112.25971320528504,"max_cost":961.2237943202531},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":8192,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-a-03-2025","alias_ids":null,"forwarded_model_id":null},{"id":"reka-flash-3","name":"Reka Flash 3","created":1741812813,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.012976040000000001,"max_cost":0.013696980000000001},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":8.980777056422802,"max_completion_cost":16.16528907293487,"max_cost":17.063421592890236},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"rekaai/reka-flash-3","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"gemma-3-27b-it","name":"Google: Gemma 3 27B","created":1741756359,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":8.800000000000001e-8,"completion":3.85e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.011534336000000001,"max_completion_cost":0.04541614,"max_cost":0.046569644},"sats_pricing":{"prompt":0.00010962862617703617,"completion":0.0004796252395245332,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000054814313088518084,"input_cache_write":0.0,"max_prompt_cost":14.369243290276485,"max_completion_cost":56.57851175527203,"max_cost":58.01552378720062},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-3-27b-it","alias_ids":null,"forwarded_model_id":null},{"id":"skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","created":1741636566,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.05e-7,"completion":8.8e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.01982464,"max_completion_cost":0.025952080000000002,"max_cost":0.027934665000000004},"sats_pricing":{"prompt":0.0007536968049671235,"completion":0.0010962862617703616,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000342589456803238,"input_cache_write":0.0,"max_prompt_cost":24.697136905162704,"max_completion_cost":32.33057814586974,"max_cost":34.800442575747},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thedrummer/skyfall-36b-v2","alias_ids":null,"forwarded_model_id":null},{"id":"sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","created":1741313308,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":2.2e-6,"completion":8.8e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":1.01376,"max_cost":1.04192},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.010962862617703616,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":350.8116037665157,"max_completion_cost":1262.9217735594564,"max_cost":1298.002933936108},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-reasoning-pro","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"sonar-pro","name":"Perplexity: Sonar Pro","created":1741312423,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.66,"max_completion_cost":0.132,"max_cost":0.7656000000000001},"sats_pricing":{"prompt":0.004111073481638856,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":822.2146963277712,"max_completion_cost":164.44293926555423,"max_cost":953.7690477402147},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-pro","alias_ids":null,"forwarded_model_id":null},{"id":"sonar-deep-research","name":"Perplexity: Sonar Deep Research","created":1741311246,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":2.2e-6,"completion":8.8e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":3.3e-6,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":1.01376,"max_cost":1.04192},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.010962862617703616,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.004111073481638856,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":350.8116037665157,"max_completion_cost":1262.9217735594564,"max_cost":1298.002933936108},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-deep-research","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"mistral-saba","name":"Mistral: Saba","created":1739803239,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","context_length":32768,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.017301240000000002,"max_cost":0.018743120000000002},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027407156544259042,"input_cache_write":0.0,"max_prompt_cost":8.980777056422802,"max_completion_cost":21.553536049536195,"max_cost":23.34980108944693},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-saba-2502","alias_ids":null,"forwarded_model_id":null},{"id":"aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","created":1738696718,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":1.76e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.051904160000000005,"max_cost":0.054787920000000004},"sats_pricing":{"prompt":0.0010962862617703616,"completion":0.002192572523540723,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":35.92310822569121,"max_completion_cost":64.66115629173947,"max_cost":68.25368637156095},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-rp-llama-3.1-8b","alias_ids":null,"forwarded_model_id":null},{"id":"qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","created":1738410311,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":0.0,"max_prompt_cost":0.11264,"max_completion_cost":0.12672,"max_cost":0.137984},"sats_pricing":{"prompt":0.0010962862617703616,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005481431308851808,"input_cache_write":0.0,"max_prompt_cost":140.32464150660627,"max_completion_cost":157.86522169493205,"max_cost":171.8976858455927},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen2.5-vl-72b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"qwen-plus","name":"Qwen: Qwen-Plus","created":1738409840,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.8600000000000005e-7,"completion":8.580000000000001e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.720000000000001e-8,"input_cache_write":3.575e-7,"max_prompt_cost":0.28600000000000003,"max_completion_cost":0.028114944000000003,"max_cost":0.30474329600000005},"sats_pricing":{"prompt":0.00035629303507536756,"completion":0.0010688791052261026,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00007125860701507352,"input_cache_write":0.00044536629384420937,"max_prompt_cost":356.2930350753675,"max_completion_cost":35.02503052004893,"max_cost":379.6430554220668},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-plus-2025-01-25","alias_ids":null,"forwarded_model_id":null},{"id":"o3-mini:batch","name":"OpenAI: o3 Mini (batch)","created":1738351721,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...","context_length":200000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.05e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":3.025e-7,"input_cache_write":0.0,"max_prompt_cost":0.12100000000000001,"max_completion_cost":0.24200000000000002,"max_cost":0.30250000000000005},"sats_pricing":{"prompt":0.0007536968049671235,"completion":0.003014787219868494,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.00037684840248356177,"input_cache_write":0.0,"max_prompt_cost":150.73936099342473,"max_completion_cost":301.47872198684945,"max_cost":376.8484024835618},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o3-mini-2025-01-31","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true}},{"id":"mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","created":1738255409,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":8.800000000000001e-8,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00180224,"max_completion_cost":0.0014417920000000001,"max_cost":0.002342912},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.00010962862617703617,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.2451942641057006,"max_completion_cost":1.7961554112845606,"max_cost":2.9187525433374106},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-24b-instruct-2501","alias_ids":null,"forwarded_model_id":null},{"id":"sonar","name":"Perplexity: Sonar","created":1738013808,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","context_length":127072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.13977920000000002,"max_completion_cost":0.1258004,"max_cost":0.13977920000000002},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":6.8517891360647605,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":174.13410981960425,"max_completion_cost":156.71960255138205,"max_cost":174.13410981960425},"per_request_limits":null,"top_provider":{"context_length":127072,"max_completion_tokens":114364,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar","alias_ids":null,"forwarded_model_id":null},{"id":"minimax-01","name":"MiniMax: MiniMax-01","created":1736915462,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...","context_length":1000192,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.21e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.22004224,"max_completion_cost":1.0892081200000001,"max_cost":1.11121252},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.001507393609934247,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":274.12418718315536,"max_completion_cost":1356.913520641731,"max_cost":1384.326158617299},"per_request_limits":null,"top_provider":{"context_length":1000192,"max_completion_tokens":900172,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-01","alias_ids":null,"forwarded_model_id":null},{"id":"phi-4","name":"Microsoft: Phi 4","created":1736489872,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.700000000000001e-8,"completion":1.5400000000000003e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0012615680000000002,"max_completion_cost":0.0022707300000000003,"max_cost":0.0023969330000000004},"sats_pricing":{"prompt":0.00009592504790490665,"completion":0.0001918500958098133,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.5716359848739905,"max_completion_cost":2.8288296627156972,"max_cost":2.986050816231839},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":14745,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"microsoft/phi-4","alias_ids":null,"forwarded_model_id":null},{"id":"deepseek-chat","name":"DeepSeek: DeepSeek V3","created":1735241320,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":2.8314000000000003e-7,"completion":1.1315700000000001e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.0800000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.036241920000000004,"max_completion_cost":0.018105120000000002,"max_cost":0.04981680000000001},"sats_pricing":{"prompt":0.00035273010472461385,"completion":0.0014096870968539638,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003837001916196266,"input_cache_write":0.0,"max_prompt_cost":45.149453404750574,"max_completion_cost":22.554993549663422,"max_cost":62.06076527882018},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-chat-v3","alias_ids":null,"forwarded_model_id":null},{"id":"command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","created":1734158152,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":4.125e-8,"completion":1.65e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00528,"max_completion_cost":0.00066,"max_cost":0.005775000000000001},"sats_pricing":{"prompt":0.0000513884185204857,"completion":0.0002055536740819428,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.577717570622169,"max_completion_cost":0.8222146963277711,"max_cost":7.194378592867999},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-r7b-12-2024","alias_ids":null,"forwarded_model_id":null},{"id":"llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","created":1733506137,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":2.2e-7,"completion":5.720000000000001e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.07321600000000002,"max_cost":0.07389184000000001},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0007125860701507351,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001370357827212952,"input_cache_write":0.0,"max_prompt_cost":35.92310822569121,"max_completion_cost":91.2110169792941,"max_cost":92.05296482833373},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.3-70b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"nova-lite-v1","name":"Amazon: Nova Lite 1.0","created":1733437363,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":2.64e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.019799999999999998,"max_completion_cost":0.0013516799999999999,"max_cost":0.02081376},"sats_pricing":{"prompt":0.00008222146963277711,"completion":0.00032888587853110844,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":24.666440889833133,"max_completion_cost":1.6838956980792752,"max_cost":25.92936266339259},"per_request_limits":null,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-lite-v1","alias_ids":null,"forwarded_model_id":null},{"id":"nova-micro-v1","name":"Amazon: Nova Micro 1.0","created":1733437237,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":3.850000000000001e-8,"completion":1.5400000000000003e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004928000000000001,"max_completion_cost":0.0007884800000000001,"max_cost":0.005519360000000001},"sats_pricing":{"prompt":0.00004796252395245332,"completion":0.0001918500958098133,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.1392030659140255,"max_completion_cost":0.9822724905462441,"max_cost":6.875907433823708},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":5120,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-micro-v1","alias_ids":null,"forwarded_model_id":null},{"id":"nova-pro-v1","name":"Amazon: Nova Pro 1.0","created":1733436303,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":3.52e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.264,"max_completion_cost":0.0180224,"max_cost":0.2775168},"sats_pricing":{"prompt":0.0010962862617703616,"completion":0.004385145047081446,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":328.88587853110846,"max_completion_cost":22.451942641057006,"max_cost":345.72483551190123},"per_request_limits":null,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-pro-v1","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","created":1732127594,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3750000000000002e-6,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18022400000000002,"max_cost":0.48716800000000005},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0017129472840161902,"input_cache_write":0.0,"max_prompt_cost":438.51450470814467,"max_completion_cost":224.51942641057008,"max_cost":606.9040745160722},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-2024-11-20","alias_ids":null,"forwarded_model_id":null},{"id":"mistral-large-2407","name":"Mistral Large 2407","created":1731978415,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","context_length":131072,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.2883584,"max_completion_cost":0.6920562,"max_cost":0.7497292},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":359.2310822569121,"max_completion_cost":862.149664128411,"max_cost":933.997525009186},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large-2407","alias_ids":null,"forwarded_model_id":null},{"id":"qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","created":1731368400,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":7.260000000000001e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.023789568000000004,"max_completion_cost":0.0324401,"max_cost":0.034819202},"sats_pricing":{"prompt":0.0009044361659605484,"completion":0.001370357827212952,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":29.63656428619525,"max_completion_cost":40.413222682337164,"max_cost":43.377059998189885},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-2.5-coder-32b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","created":1731103448,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","context_length":1024000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":4.4e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.45056,"max_completion_cost":0.360448,"max_cost":0.45055999999999996},"sats_pricing":{"prompt":0.0005481431308851808,"completion":0.0005481431308851808,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":561.2985660264251,"max_completion_cost":449.0388528211401,"max_cost":561.2985660264251},"per_request_limits":null,"top_provider":{"context_length":1024000,"max_completion_tokens":819200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thedrummer/unslopnemo-12b","alias_ids":null,"forwarded_model_id":null},{"id":"magnum-v4-72b","name":"Magnum v4 72B","created":1729555200,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":2.7500000000000004e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.09011200000000001,"max_completion_cost":0.022528000000000003,"max_cost":0.10137600000000002},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":112.25971320528504,"max_completion_cost":28.06492830132126,"max_cost":126.29217735594567},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthracite-org/magnum-v4-72b","alias_ids":null,"forwarded_model_id":null},{"id":"qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","created":1729036800,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00360448,"max_completion_cost":0.006488020000000001,"max_cost":0.0068484900000000005},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.490388528211401,"max_completion_cost":8.082644536467434,"max_cost":8.531710796445118},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-2.5-7b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","created":1727222400,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...","context_length":60000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":2.97e-8,"completion":2.2110000000000004e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0017820000000000002,"max_completion_cost":0.011939400000000003,"max_cost":0.012117600000000003},"sats_pricing":{"prompt":0.0000369996613347497,"completion":0.0002754419232698034,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.2199796800849825,"max_completion_cost":14.873863856569384,"max_cost":15.09586182457788},"per_request_limits":null,"top_provider":{"context_length":60000,"max_completion_tokens":54000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.2-1b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","created":1727222400,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":5.599e-8,"completion":3.6850000000000005e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0044792,"max_completion_cost":0.026532000000000003,"max_cost":0.026979920000000004},"sats_pricing":{"prompt":0.00006975121340513925,"completion":0.00045906987211633894,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.5800970724111405,"max_completion_cost":33.053030792376404,"max_cost":33.611040499617516},"per_request_limits":null,"top_provider":{"context_length":80000,"max_completion_tokens":72000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.2-3b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","created":1726704000,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":3.9600000000000005e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.012976128000000002,"max_completion_cost":0.00720896,"max_cost":0.013697024000000002},"sats_pricing":{"prompt":0.0004933288177966628,"completion":0.0005481431308851808,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":16.165398701561045,"max_completion_cost":8.980777056422802,"max_cost":17.063476407203325},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-2.5-72b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"command-r-08-2024","name":"Cohere: Command R (08-2024)","created":1724976000,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02112,"max_completion_cost":0.00264,"max_cost":0.023100000000000002},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":26.310870282488676,"max_completion_cost":3.2888587853110844,"max_cost":28.777514371471995},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-r-08-2024","alias_ids":null,"forwarded_model_id":null},{"id":"command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","created":1724976000,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.044000000000000004,"max_cost":0.385},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":438.51450470814467,"max_completion_cost":54.814313088518084,"max_cost":479.6252395245332},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-r-plus-08-2024","alias_ids":null,"forwarded_model_id":null},{"id":"l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","created":1724803200,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":9.35e-7,"completion":9.35e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.12255232,"max_completion_cost":0.01531904,"max_cost":0.12255232},"sats_pricing":{"prompt":0.0011648041531310091,"completion":0.0011648041531310091,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":152.67320995918763,"max_completion_cost":19.084151244898454,"max_cost":152.67320995918763},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sao10k/l3.1-euryale-70b","alias_ids":null,"forwarded_model_id":null},{"id":"l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","created":1723507200,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":4.4000000000000004e-8,"completion":5.5e-8,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00036044800000000003,"max_completion_cost":0.00040546,"max_cost":0.00044154000000000003},"sats_pricing":{"prompt":0.000054814313088518084,"completion":0.0000685178913606476,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.44903885282114014,"max_completion_cost":0.505113895110694,"max_cost":0.5500616318432789},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":7372,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sao10k/l3-lunaris-8b","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","created":1722902400,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3750000000000002e-6,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18022400000000002,"max_cost":0.48716800000000005},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0017129472840161902,"input_cache_write":0.0,"max_prompt_cost":438.51450470814467,"max_completion_cost":224.51942641057008,"max_cost":606.9040745160722},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-2024-08-06","alias_ids":null,"forwarded_model_id":null},{"id":"llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":7.920000000000001e-7,"completion":7.920000000000001e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.10380902400000001,"max_completion_cost":0.006488064000000001,"max_cost":0.10380902400000001},"sats_pricing":{"prompt":0.0009866576355933255,"completion":0.0009866576355933255,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":129.32318961248836,"max_completion_cost":8.082699350780523,"max_cost":129.32318961248836},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.1-70b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":5.5e-8,"completion":8.800000000000001e-8,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.010380832000000001,"max_cost":0.011101772000000001},"sats_pricing":{"prompt":0.0000685178913606476,"completion":0.00010962862617703617,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000342589456803238,"input_cache_write":0.0,"max_prompt_cost":8.980777056422802,"max_completion_cost":12.932231258347894,"max_cost":13.830363778303262},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.1-8b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"mistral-nemo","name":"Mistral: Mistral Nemo","created":1721347200,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3.19e-8,"completion":3.3e-8,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0041811968,"max_completion_cost":0.000540672,"max_cost":0.0041992192},"sats_pricing":{"prompt":0.000039740376989175604,"completion":0.000041110734816388555,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.208850692725225,"max_completion_cost":0.6735582792317101,"max_cost":5.231302635366282},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-nemo","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4o-mini","name":"OpenAI: GPT-4o-mini","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.02112,"max_completion_cost":0.01081344,"max_cost":0.029230080000000002},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001027768370409714,"input_cache_write":0.0,"max_prompt_cost":26.310870282488676,"max_completion_cost":13.471165584634203,"max_cost":36.414244470964334},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-mini","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.02112,"max_completion_cost":0.01081344,"max_cost":0.029230080000000002},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001027768370409714,"input_cache_write":0.0,"max_prompt_cost":26.310870282488676,"max_completion_cost":13.471165584634203,"max_cost":36.414244470964334},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-mini-2024-07-18","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4o-mini:batch","name":"OpenAI: GPT-4o-mini (batch)","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.01056,"max_completion_cost":0.00540672,"max_cost":0.014615040000000001},"sats_pricing":{"prompt":0.0001027768370409714,"completion":0.0004111073481638856,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0000513884185204857,"input_cache_write":0.0,"max_prompt_cost":13.155435141244338,"max_completion_cost":6.735582792317102,"max_cost":18.207122235482167},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-mini","alias_ids":null,"forwarded_model_id":null},{"id":"gemma-2-27b-it","name":"Google: Gemma 2 27B","created":1720828800,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":7.15e-7,"completion":7.15e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00585728,"max_completion_cost":0.00146432,"max_cost":0.00585728},"sats_pricing":{"prompt":0.0008907325876884187,"completion":0.0008907325876884187,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.296881358343526,"max_completion_cost":1.8242203395858816,"max_cost":7.296881358343526},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":2048,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-2-27b-it","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4o","name":"OpenAI: GPT-4o","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3750000000000002e-6,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18022400000000002,"max_cost":0.48716800000000005},"sats_pricing":{"prompt":0.0034258945680323803,"completion":0.013703578272129521,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0017129472840161902,"input_cache_write":0.0,"max_prompt_cost":438.51450470814467,"max_completion_cost":224.51942641057008,"max_cost":606.9040745160722},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.7040000000000001,"max_completion_cost":0.067584,"max_cost":0.749056},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":877.0290094162893,"max_completion_cost":84.19478490396378,"max_cost":933.1588660189318},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-2024-05-13","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4o:batch","name":"OpenAI: GPT-4o (batch)","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":6.875000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":0.17600000000000002,"max_completion_cost":0.09011200000000001,"max_cost":0.24358400000000002},"sats_pricing":{"prompt":0.0017129472840161902,"completion":0.006851789136064761,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0008564736420080951,"input_cache_write":0.0,"max_prompt_cost":219.25725235407234,"max_completion_cost":112.25971320528504,"max_cost":303.4520372580361},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o","alias_ids":null,"forwarded_model_id":null},{"id":"mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","created":1713312000,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","context_length":65536,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.3460248,"max_cost":0.37486240000000004},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":179.61554112845604,"max_completion_cost":431.0707209907239,"max_cost":466.99602178893866},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":52428,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mixtral-8x22b-instruct","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4-turbo:batch","name":"OpenAI: GPT-4 Turbo (batch)","created":1712620800,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.0000165,"request":0.0,"image":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.7040000000000001,"max_completion_cost":0.067584,"max_cost":0.749056},"sats_pricing":{"prompt":0.006851789136064761,"completion":0.020555367408194282,"request":0.001,"image":0.0,"web_search":13.703578272129521,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":877.0290094162893,"max_completion_cost":84.19478490396378,"max_cost":933.1588660189318},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4-turbo","alias_ids":null,"forwarded_model_id":null},{"id":"mistral-large","name":"Mistral Large","created":1708905600,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","context_length":128000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":0.67584,"max_cost":0.73216},"sats_pricing":{"prompt":0.002740715654425904,"completion":0.008222146963277712,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002740715654425904,"input_cache_write":0.0,"max_prompt_cost":350.8116037665157,"max_completion_cost":841.9478490396376,"max_cost":912.1101697929408},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","created":1706140800,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","context_length":4095,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0045045,"max_completion_cost":0.008107,"max_cost":0.008558},"sats_pricing":{"prompt":0.001370357827212952,"completion":0.002740715654425904,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.611615302437038,"max_completion_cost":10.099537186559456,"max_cost":10.661383895716765},"per_request_limits":null,"top_provider":{"context_length":4095,"max_completion_tokens":3685,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-3.5-turbo-0613","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","created":1693180800,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","context_length":16385,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0540705,"max_completion_cost":0.0180224,"max_cost":0.058576100000000006},"sats_pricing":{"prompt":0.004111073481638856,"completion":0.005481431308851808,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":67.35993899665266,"max_completion_cost":22.451942641057006,"max_cost":72.97292465691692},"per_request_limits":null,"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-3.5-turbo-16k","alias_ids":null,"forwarded_model_id":null},{"id":"weaver","name":"Mancer: Weaver (alpha)","created":1690934400,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","context_length":8000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":4.4e-7,"completion":8.25e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00352,"max_completion_cost":0.00495,"max_cost":0.00583},"sats_pricing":{"prompt":0.0005481431308851808,"completion":0.001027768370409714,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.385145047081446,"max_completion_cost":6.166610222458284,"max_cost":7.262896484228645},"per_request_limits":null,"top_provider":{"context_length":8000,"max_completion_tokens":6000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mancer/weaver","alias_ids":null,"forwarded_model_id":null},{"id":"remm-slerp-l2-13b","name":"ReMM SLERP 13B","created":1689984000,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","context_length":6144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":3.85e-7,"completion":7.15e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00236544,"max_completion_cost":0.003953235,"max_cost":0.00419001},"sats_pricing":{"prompt":0.0004796252395245332,"completion":0.0008907325876884187,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.946817471638732,"max_completion_cost":4.9248604773292675,"max_cost":5.219829999636855},"per_request_limits":null,"top_provider":{"context_length":6144,"max_completion_tokens":5529,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"undi95/remm-slerp-l2-13b","alias_ids":null,"forwarded_model_id":null},{"id":"mythomax-l2-13b","name":"MythoMax 13B","created":1688256000,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":8.800000000000001e-8,"completion":1.21e-7,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00036044800000000003,"max_completion_cost":0.00044600600000000004,"max_cost":0.00048208600000000006},"sats_pricing":{"prompt":0.00010962862617703617,"completion":0.00015073936099342474,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.44903885282114014,"max_completion_cost":0.5556252846217635,"max_cost":0.6005730213543484},"per_request_limits":null,"top_provider":{"context_length":4096,"max_completion_tokens":3686,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"gryphe/mythomax-l2-13b","alias_ids":null,"forwarded_model_id":null},{"id":"gpt-4","name":"OpenAI: GPT-4","created":1685232000,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","context_length":8191,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000033,"completion":0.000066,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.270303,"max_completion_cost":0.270336,"max_cost":0.405471},"sats_pricing":{"prompt":0.041110734816388564,"completion":0.08222146963277713,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":336.7380288810387,"max_completion_cost":336.7791396158551,"max_cost":505.12759868896626},"per_request_limits":null,"top_provider":{"context_length":8191,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4","alias_ids":null,"forwarded_model_id":null},{"id":"embed-5-fast","name":"Cohere: Embed 5 Fast","created":1793739025,"description":"Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). It embeds text, images, and interleaved text and image content...","context_length":128000,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":8.800000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.011264000000000001,"max_completion_cost":0.0,"max_cost":0.011264000000000001},"sats_pricing":{"prompt":0.00010962862617703617,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":14.03246415066063,"max_completion_cost":0.0,"max_cost":14.03246415066063},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/embed-5-fast-20261029","alias_ids":null,"forwarded_model_id":null},{"id":"embed-5-pro","name":"Cohere: Embed 5 Pro","created":1793739016,"description":"Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). It embeds text, images, and interleaved text and image content into...","context_length":128000,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.016895999999999998,"max_completion_cost":0.0,"max_cost":0.016895999999999998},"sats_pricing":{"prompt":0.00016444293926555422,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":21.048696225990938,"max_completion_cost":0.0,"max_cost":21.048696225990938},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/embed-5-pro-20261029","alias_ids":null,"forwarded_model_id":null},{"id":"titan-embed-image-v1","name":"Amazon: Titan Multimodal Embeddings G1","created":1793044729,"description":"Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. Images are sent as base64 (up to...","context_length":128,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":0.0,"request":0.0,"image":0.000066,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00011264,"max_completion_cost":0.0,"max_cost":0.00011264},"sats_pricing":{"prompt":0.0010962862617703616,"completion":0.0,"request":0.001,"image":0.08222146963277713,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.14032464150660628,"max_completion_cost":0.0,"max_cost":0.14032464150660628},"per_request_limits":null,"top_provider":{"context_length":128,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/titan-embed-image-v1-20261026","alias_ids":null,"forwarded_model_id":null},{"id":"titan-embed-text-v1","name":"Amazon: Titan Embeddings G1 - Text","created":1793044727,"description":"Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model. It accepts up to 8,192 tokens per input and returns fixed 1,536-dimension vectors; the `dimensions` parameter is...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00090112,"max_completion_cost":0.0,"max_cost":0.00090112},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.1225971320528503,"max_completion_cost":0.0,"max_cost":1.1225971320528503},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/titan-embed-text-v1-20261026","alias_ids":null,"forwarded_model_id":null},{"id":"titan-embed-text-v2","name":"Amazon: Titan Text Embeddings V2","created":1793044722,"description":"Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering. It accepts up to 8,192 tokens per input and returns normalized vectors of 1,024 dimensions...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00018022400000000001,"max_completion_cost":0.0,"max_cost":0.00018022400000000001},"sats_pricing":{"prompt":0.000027407156544259042,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.22451942641057007,"max_completion_cost":0.0,"max_cost":0.22451942641057007},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/titan-embed-text-v2-20261026","alias_ids":null,"forwarded_model_id":null},{"id":"voyage-code-4","name":"VoyageAI by MongoDB: voyage-code-4","created":1786636912,"description":"voyage-code-4 is a code embedding model from Voyage AI, a MongoDB company. It is designed for coding agents and code retrieval, with Matryoshka embeddings at 2048t voyage-code-4 here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0042239999999999995,"max_completion_cost":0.0,"max_cost":0.0042239999999999995},"sats_pricing":{"prompt":0.00016444293926555422,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.262174056497734,"max_completion_cost":0.0,"max_cost":5.262174056497734},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-code-4-20260812","alias_ids":null,"forwarded_model_id":null},{"id":"voyage-multimodal-3.5","name":"VoyageAI by MongoDB: voyage-multimodal-3.5","created":1785188629,"description":"voyage-multimodal-3.5 is a state-of-the-art multimodal embedding model capable of vectorizing not only text, images, and video individually, but also content that interleaves all three modalities. It delivers excellent performance for...","context_length":32000,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0042239999999999995,"max_completion_cost":0.0,"max_cost":0.0042239999999999995},"sats_pricing":{"prompt":0.00016444293926555422,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.262174056497734,"max_completion_cost":0.0,"max_cost":5.262174056497734},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-multimodal-3.5-20260727","alias_ids":null,"forwarded_model_id":null},{"id":"voyage-4-lite","name":"VoyageAI by MongoDB: voyage-4-lite","created":1785188627,"description":"voyage-4-lite is a lightweight, general-purpose embedding model optimized for low latency and cost. Enabled by Matryoshka learning and quantization-aware training, voyage-4-lite supports embeddings t voyage-4-lite here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0007040000000000001,"max_completion_cost":0.0,"max_cost":0.0007040000000000001},"sats_pricing":{"prompt":0.000027407156544259042,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.8770290094162894,"max_completion_cost":0.0,"max_cost":0.8770290094162894},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-4-lite-20260727","alias_ids":null,"forwarded_model_id":null},{"id":"voyage-4","name":"VoyageAI by MongoDB: voyage-4","created":1785188626,"description":"voyage-4 is a general-purpose (including multilingual) embedding model optimized for retrieval/search and AI applications. voyage-4 supports embedd about voyage-4 here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0021119999999999997,"max_completion_cost":0.0,"max_cost":0.0021119999999999997},"sats_pricing":{"prompt":0.00008222146963277711,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.631087028248867,"max_completion_cost":0.0,"max_cost":2.631087028248867},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-4-20260727","alias_ids":null,"forwarded_model_id":null},{"id":"voyage-4-large","name":"VoyageAI by MongoDB: voyage-4-large","created":1785188624,"description":"voyage-4-large is a state-of-the-art general-purpose and multilingual embedding optimized for retrieval quality. Enabled by Matryoshka learning and quantization-aware training, voyage-4-large supports embeddings  voyage-4-large here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0042239999999999995,"max_completion_cost":0.0,"max_cost":0.0042239999999999995},"sats_pricing":{"prompt":0.00016444293926555422,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.262174056497734,"max_completion_cost":0.0,"max_cost":5.262174056497734},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-4-large-20260727","alias_ids":null,"forwarded_model_id":null},{"id":"gemini-embedding-2","name":"Google: Gemini Embedding 2","created":1779290135,"description":"Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports...","context_length":8192,"architecture":{"modality":"text+image+file+audio+video->embeddings","input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":0.0,"request":0.0,"image":4.95e-7,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00180224,"max_completion_cost":0.0,"max_cost":0.00180224},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0,"request":0.001,"image":0.0006166610222458283,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.2451942641057006,"max_completion_cost":0.0,"max_cost":2.2451942641057006},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-embedding-2","alias_ids":null,"forwarded_model_id":null},{"id":"gemini-embedding-2-preview","name":"Google: Gemini Embedding 2 Preview","created":1776436465,"description":"Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It...","context_length":8192,"architecture":{"modality":"text+image+file+audio+video->embeddings","input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":0.0,"request":0.0,"image":4.95e-7,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00180224,"max_completion_cost":0.0,"max_cost":0.00180224},"sats_pricing":{"prompt":0.0002740715654425904,"completion":0.0,"request":0.001,"image":0.0006166610222458283,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.2451942641057006,"max_completion_cost":0.0,"max_cost":2.2451942641057006},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-embedding-2-preview","alias_ids":null,"forwarded_model_id":null},{"id":"pplx-embed-v1-4b","name":"Perplexity: Embed V1 4B","created":1773625372,"description":"pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter model maximizing retrieval...","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0010559999999999999,"max_completion_cost":0.0,"max_cost":0.0010559999999999999},"sats_pricing":{"prompt":0.000041110734816388555,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.3155435141244336,"max_completion_cost":0.0,"max_cost":1.3155435141244336},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/pplx-embed-v1-4B","alias_ids":null,"forwarded_model_id":null},{"id":"pplx-embed-v1-0.6b","name":"Perplexity: Embed V1 0.6B","created":1773624868,"description":"pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency...","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4000000000000005e-9,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0001408,"max_completion_cost":0.0,"max_cost":0.0001408},"sats_pricing":{"prompt":5.481431308851808e-6,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.17540580188325786,"max_completion_cost":0.0,"max_cost":0.17540580188325786},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/pplx-embed-v1-0.6B","alias_ids":null,"forwarded_model_id":null},{"id":"gte-base","name":"Thenlper: GTE-Base","created":1763433820,"description":"The gte-base embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, delivering efficient and effective semantic embeddings optimized for textual similarity, semantic search, and clustering applications.","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.8517891360647605e-6,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035081160376651574,"max_completion_cost":0.0,"max_cost":0.0035081160376651574},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thenlper/gte-base-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"gte-large","name":"Thenlper: GTE-Large","created":1763433655,"description":"The gte-large embedding model converts English sentences, paragraphs and moderate-length documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for information retrieval, semantic textual similarity, reranking and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.6320000000000005e-6,"max_completion_cost":0.0,"max_cost":5.6320000000000005e-6},"sats_pricing":{"prompt":0.000013703578272129521,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007016232075330315,"max_completion_cost":0.0,"max_cost":0.007016232075330315},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thenlper/gte-large-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"e5-large-v2","name":"Intfloat: E5-Large-v2","created":1763433432,"description":"The e5-large-v2 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-accuracy semantic embeddings optimized for retrieval, semantic search, reranking, and similarity-scoring tasks.","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.6320000000000005e-6,"max_completion_cost":0.0,"max_cost":5.6320000000000005e-6},"sats_pricing":{"prompt":0.000013703578272129521,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007016232075330315,"max_completion_cost":0.0,"max_cost":0.007016232075330315},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"intfloat/e5-large-v2-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"e5-base-v2","name":"Intfloat: E5-Base-v2","created":1763433192,"description":"The e5-base-v2 embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, similarity scoring,...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.8517891360647605e-6,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035081160376651574,"max_completion_cost":0.0,"max_cost":0.0035081160376651574},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"intfloat/e5-base-v2-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"multilingual-e5-large","name":"Intfloat: Multilingual-E5-Large","created":1763433047,"description":"The multilingual-e5-large embedding model encodes sentences, paragraphs, and documents across over 90 languages into a 1024-dimensional dense vector space, delivering robust semantic embeddings optimized for multilingual retrieval, cross-language similarity, and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.6320000000000005e-6,"max_completion_cost":0.0,"max_cost":5.6320000000000005e-6},"sats_pricing":{"prompt":0.000013703578272129521,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007016232075330315,"max_completion_cost":0.0,"max_cost":0.007016232075330315},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"intfloat/multilingual-e5-large-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"paraphrase-minilm-l6-v2","name":"Sentence Transformers: paraphrase-MiniLM-L6-v2","created":1763432454,"description":"The paraphrase-MiniLM-L6-v2 embedding model converts sentences and short paragraphs into a 384-dimensional dense vector space, producing high-quality semantic embeddings optimized for paraphrase detection, semantic similarity scoring, clustering, and lightweight retrieval...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.8517891360647605e-6,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035081160376651574,"max_completion_cost":0.0,"max_cost":0.0035081160376651574},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/paraphrase-minilm-l6-v2-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"all-minilm-l12-v2","name":"Sentence Transformers: all-MiniLM-L12-v2","created":1763432155,"description":"The all-MiniLM-L12-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, clustering, and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.8517891360647605e-6,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035081160376651574,"max_completion_cost":0.0,"max_cost":0.0035081160376651574},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/all-minilm-l12-v2-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"bge-base-en-v1.5","name":"BAAI: bge-base-en-v1.5","created":1763431837,"description":"The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. This version (v1.5) features...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.8517891360647605e-6,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035081160376651574,"max_completion_cost":0.0,"max_cost":0.0035081160376651574},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"baai/bge-base-en-v1.5-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"multi-qa-mpnet-base-dot-v1","name":"Sentence Transformers: multi-qa-mpnet-base-dot-v1","created":1763431339,"description":"The multi-qa-mpnet-base-dot-v1 embedding model transforms sentences and short paragraphs into a 768-dimensional dense vector space, generating high-quality semantic embeddings optimized for question-and-answer retrieval, semantic search, and similarity-scoring across diverse content.","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.8517891360647605e-6,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035081160376651574,"max_completion_cost":0.0,"max_cost":0.0035081160376651574},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"bge-large-en-v1.5","name":"BAAI: bge-large-en-v1.5","created":1763431087,"description":"The bge-large-en-v1.5 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-fidelity semantic embeddings optimized for semantic search, document retrieval, and downstream NLP tasks...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.6320000000000005e-6,"max_completion_cost":0.0,"max_cost":5.6320000000000005e-6},"sats_pricing":{"prompt":0.000013703578272129521,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007016232075330315,"max_completion_cost":0.0,"max_cost":0.007016232075330315},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"baai/bge-large-en-v1.5-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"bge-m3","name":"BAAI: bge-m3","created":1763424372,"description":"The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.","context_length":8194,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.000090134,"max_completion_cost":0.0,"max_cost":0.000090134},"sats_pricing":{"prompt":0.000013703578272129521,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.11228712036182928,"max_completion_cost":0.0,"max_cost":0.11228712036182928},"per_request_limits":null,"top_provider":{"context_length":8194,"max_completion_tokens":8194,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"baai/bge-m3-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"all-mpnet-base-v2","name":"Sentence Transformers: all-mpnet-base-v2","created":1763421830,"description":"The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a 768-dimensional dense vector space, providing high-fidelity semantic embeddings well suited for tasks like information retrieval, clustering, similarity scoring, and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.8517891360647605e-6,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035081160376651574,"max_completion_cost":0.0,"max_cost":0.0035081160376651574},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/all-mpnet-base-v2-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"all-minilm-l6-v2","name":"Sentence Transformers: all-MiniLM-L6-v2","created":1763421176,"description":"The all-MiniLM-L6-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, enabling high-quality semantic representations that are ideal for downstream tasks such as information retrieval, clustering,...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.8517891360647605e-6,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035081160376651574,"max_completion_cost":0.0,"max_cost":0.0035081160376651574},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/all-minilm-l6-v2-20251117","alias_ids":null,"forwarded_model_id":null},{"id":"mistral-embed-2312","name":"Mistral: Mistral Embed 2312","created":1761944622,"description":"Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00090112,"max_completion_cost":0.0,"max_cost":0.00090112},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.1225971320528503,"max_completion_cost":0.0,"max_cost":1.1225971320528503},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-embed-2312","alias_ids":null,"forwarded_model_id":null},{"id":"gemini-embedding-001","name":"Google: Gemini Embedding 001","created":1761943410,"description":"gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark...","context_length":20000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0033,"max_completion_cost":0.0,"max_cost":0.0033},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.111073481638856,"max_completion_cost":0.0,"max_cost":4.111073481638856},"per_request_limits":null,"top_provider":{"context_length":20000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-embedding-001","alias_ids":null,"forwarded_model_id":null},{"id":"text-embedding-ada-002","name":"OpenAI: Text Embedding Ada 002","created":1761865798,"description":"text-embedding-ada-002 is OpenAI's legacy text embedding model.","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00090112,"max_completion_cost":0.0,"max_cost":0.00090112},"sats_pricing":{"prompt":0.0001370357827212952,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.1225971320528503,"max_completion_cost":0.0,"max_cost":1.1225971320528503},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/text-embedding-ada-002","alias_ids":["text-embedding-ada-002-v2"],"forwarded_model_id":null},{"id":"codestral-embed-2505","name":"Mistral: Codestral Embed 2505","created":1761864460,"description":"Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00135168,"max_completion_cost":0.0,"max_cost":0.00135168},"sats_pricing":{"prompt":0.0002055536740819428,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.6838956980792754,"max_completion_cost":0.0,"max_cost":1.6838956980792754},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/codestral-embed-2505","alias_ids":null,"forwarded_model_id":null},{"id":"text-embedding-3-large","name":"OpenAI: Text Embedding 3 Large","created":1761862866,"description":"text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.4300000000000002e-7,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0011714560000000002,"max_completion_cost":0.0,"max_cost":0.0011714560000000002},"sats_pricing":{"prompt":0.00017814651753768378,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.4593762716687055,"max_completion_cost":0.0,"max_cost":1.4593762716687055},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/text-embedding-3-large","alias_ids":null,"forwarded_model_id":null},{"id":"text-embedding-3-small","name":"OpenAI: Text Embedding 3 Small","created":1761857455,"description":"text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00018022400000000001,"max_completion_cost":0.0,"max_cost":0.00018022400000000001},"sats_pricing":{"prompt":0.000027407156544259042,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.22451942641057007,"max_completion_cost":0.0,"max_cost":0.22451942641057007},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/text-embedding-3-small","alias_ids":null,"forwarded_model_id":null},{"id":"qwen3-embedding-8b","name":"Qwen: Qwen3 Embedding 8B","created":1761680622,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text...","context_length":40960,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00045056,"max_completion_cost":0.0,"max_cost":0.00009856},"sats_pricing":{"prompt":0.000013703578272129521,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.5612985660264251,"max_completion_cost":0.0,"max_cost":0.1227840613182805},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":32000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-embedding-8b","alias_ids":null,"forwarded_model_id":null},{"id":"qwen3-embedding-4b","name":"Qwen: Qwen3 Embedding 4B","created":1761662922,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text...","context_length":32768,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0007208960000000001,"max_completion_cost":0.0,"max_cost":0.0007208960000000001},"sats_pricing":{"prompt":0.000027407156544259042,"completion":0.0,"request":0.001,"image":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.8980777056422803,"max_completion_cost":0.0,"max_cost":0.8980777056422803},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-embedding-4b","alias_ids":null,"forwarded_model_id":null}]}