{"models":[{"model_id":"auto","display_name":"Auto","provider":"dos-ai","input_price_per_million":0,"output_price_per_million":0,"context_length":131072,"description":"DOS.AI Smart Router classifies each request by complexity. Simple and Medium requests use DOS.AI; Complex requests can use an eligible paid route configured in the live catalog.","capabilities":{"category":"chat","is_new":false,"pricing":"variable","selected_models":["dos","gpt-5.6-luna","gemini-3.8-flash","qwen3.8-max"],"special_model":"router"},"created_at":"2026-04-06T04:16:12.264575+00:00","providers":[]},{"model_id":"bge-base-en-v1.5","display_name":"BGE Base EN v1.5","provider":"cloudflare","input_price_per_million":6.66,"output_price_per_million":0,"context_length":512,"capabilities":{"catalog_release":"20260907195500","category":"embedding","embedding_dims":768,"is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":6.66,"retail_out":0,"context_len":512,"data_retention":"allow","status":"enabled"}]},{"model_id":"bge-large-en-v1.5","display_name":"BGE Large EN v1.5","provider":"cloudflare","input_price_per_million":20.4,"output_price_per_million":0,"context_length":512,"capabilities":{"catalog_release":"20260907195500","category":"embedding","embedding_dims":1024,"is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":20.4,"retail_out":0,"context_len":512,"data_retention":"allow","status":"enabled"}]},{"model_id":"bge-small-en-v1.5","display_name":"BGE Small EN v1.5","provider":"cloudflare","input_price_per_million":2.02,"output_price_per_million":0,"context_length":512,"capabilities":{"catalog_release":"20260907195500","category":"embedding","embedding_dims":384,"is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":2.02,"retail_out":0,"context_len":512,"data_retention":"allow","status":"enabled"}]},{"model_id":"claude-haiku-4.5","display_name":"Claude Haiku 4.5","provider":"anthropic","input_price_per_million":105,"output_price_per_million":525,"context_length":200000,"description":"Fastest and most compact Claude model","capabilities":{"category":"chat","is_new":false,"vision":true},"created_at":"2026-04-07T14:39:27.213012+00:00","providers":[{"provider":"anthropic","display_name":"Anthropic","country":"US","retail_in":105,"retail_out":525,"context_len":200000,"data_retention":"allow","status":"enabled"}]},{"model_id":"claude-opus-5","display_name":"Claude Opus 5","provider":"anthropic","input_price_per_million":525,"output_price_per_million":2625,"context_length":1000000,"description":"Anthropic flagship model for complex agentic coding and enterprise work, with a 1M context window and up to 128K synchronous output tokens.","capabilities":{"category":"chat","code":true,"is_new":false,"max_output_tokens":128000,"reasoning":true,"released_at":"2026-07-24","series":"claude-opus","streaming":true,"tools":true,"vision":true},"created_at":"2026-08-05T04:50:37.847953+00:00","providers":[{"provider":"anthropic","display_name":"Anthropic","country":"US","retail_in":525,"retail_out":2625,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"claude-sonnet-5","display_name":"Claude Sonnet 5","provider":"anthropic","input_price_per_million":315,"output_price_per_million":1575,"context_length":1000000,"description":"Anthropic balanced model with near-flagship coding and agentic quality at Sonnet pricing, a 1M context window, and up to 128K output tokens.","capabilities":{"category":"chat","code":true,"is_new":false,"max_output_tokens":128000,"reasoning":true,"released_at":"2026-06-30","series":"claude-sonnet","streaming":true,"tools":true,"vision":true},"created_at":"2026-08-05T11:58:35.545864+00:00","providers":[{"provider":"anthropic","display_name":"Anthropic","country":"US","retail_in":315,"retail_out":1575,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"deepseek-r1-distill-qwen-32b","display_name":"DeepSeek R1 Distill Qwen 32B","provider":"cloudflare","input_price_per_million":49.7,"output_price_per_million":488.1,"context_length":80000,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":49.7,"retail_out":488.1,"context_len":80000,"data_retention":"allow","status":"enabled"}]},{"model_id":"deepseek-v4-flash","display_name":"DeepSeek V4 Flash","provider":"deepseek","input_price_per_million":21,"output_price_per_million":42,"context_length":1000000,"description":"1M-context fast tier replacing DeepSeek V3","capabilities":{"category":"chat","code":true,"is_new":false,"reasoning":true,"released_at":"2026-04-24","series":"deepseek-v4-flash"},"created_at":"2026-04-26T04:44:00.521199+00:00","providers":[{"provider":"deepseek","display_name":"DeepSeek (via Alibaba)","country":"SG","retail_in":21,"retail_out":42,"context_len":1000000,"data_retention":"allow","status":"enabled"},{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":44,"retail_out":132,"context_len":1310720,"data_retention":"allow","status":"enabled"}]},{"model_id":"deepseek-v4-pro","display_name":"DeepSeek V4 Pro","provider":"deepseek","input_price_per_million":132,"output_price_per_million":396,"context_length":1000000,"description":"Near-frontier quality at ~1/6 the cost of Opus 4.7 / GPT-5.5","capabilities":{"category":"chat","code":true,"is_new":false,"reasoning":true,"released_at":"2026-04-24","series":"deepseek-v4-pro"},"created_at":"2026-04-26T04:44:00.706971+00:00","providers":[{"provider":"deepseek","display_name":"DeepSeek (via Alibaba)","country":"SG","retail_in":252,"retail_out":504,"context_len":1000000,"data_retention":"allow","status":"enabled"},{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":132,"retail_out":396,"context_len":1048576,"data_retention":"allow","status":"enabled"}]},{"model_id":"dos","display_name":"DOS","provider":"dos-ai","input_price_per_million":7,"output_price_per_million":50,"context_length":262144,"description":"DOS curated meta-model for DOSClaw and first-party DOS products.","capabilities":{"agent_free":true,"category":"chat","code":true,"is_featured":true,"is_new":false,"reasoning":true,"selected_models":["qwen3.8-27b"],"special_model":"curated","streaming":true,"tools":true},"created_at":"2026-03-21T02:36:15.98025+00:00","providers":[]},{"model_id":"gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash-Lite","provider":"google","input_price_per_million":26,"output_price_per_million":158,"context_length":1000000,"description":"Fastest and most cost-efficient Gemini 3 model","capabilities":{"category":"chat","is_new":false,"vision":true},"created_at":"2026-04-07T16:21:45.019705+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":26,"retail_out":158,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gemini-3.1-flash-live","display_name":"Gemini 3.1 Flash Live","provider":"google","input_price_per_million":79,"output_price_per_million":473,"context_length":1000000,"description":"Real-time voice and dialogue model","capabilities":{"category":"chat","is_new":false,"vision":true},"created_at":"2026-04-07T16:21:45.019705+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":79,"retail_out":473,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gemini-3.1-pro","display_name":"Gemini 3.1 Pro","provider":"google","input_price_per_million":210,"output_price_per_million":1260,"context_length":1000000,"description":"Google's most advanced reasoning model for complex tasks","capabilities":{"category":"chat","code":true,"is_new":false,"vision":true},"created_at":"2026-04-07T16:21:45.019705+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":210,"retail_out":1260,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gemini-3.5-flash","display_name":"Gemini 3.5 Flash","provider":"google","input_price_per_million":158,"output_price_per_million":945,"context_length":1000000,"description":"Latest Gemini Flash - frontier performance, standard tier","capabilities":{"category":"chat","is_new":false,"vision":true},"created_at":"2026-06-07T09:40:27.709615+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":158,"retail_out":945,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash-Lite","provider":"google","input_price_per_million":32,"output_price_per_million":263,"context_length":1000000,"description":"Fast, cost-effective Flash-Lite (GA). 1M context. Closest Gemini peer to dos-ai (Qwen3.6-35B-A3B). [PROMO] Free when used BY a DOSClaw agent on a paid plan (agent traffic only - direct API usage is billed normally). Limited-time.","capabilities":{"category":"chat","is_new":false,"promo":true,"promo_label":"Promo","promo_note":"Free for DOSClaw agent traffic on a paid plan. Limited-time offer funded by Google Cloud credits - not permanent.","released_at":"2026-07-21","series":"gemini-flash-lite","vision":true},"created_at":"2026-07-28T08:09:20.66234+00:00","providers":[]},{"model_id":"gemini-3.7-flash","display_name":"Gemini 3.7 Flash","provider":"google","input_price_per_million":79,"output_price_per_million":394,"context_length":1000000,"description":"Google hybrid reasoning model combining fast multimodal inference with controllable thinking capabilities, a 1M context window, and up to 64K output tokens.","capabilities":{"category":"chat","code":true,"is_new":false,"max_output_tokens":65536,"reasoning":true,"released_at":"2026-02-24","series":"gemini-flash","streaming":true,"tools":true,"vision":true},"created_at":"2026-08-15T14:18:12.238197+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":79,"retail_out":394,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gemini-3.8-flash","display_name":"Gemini 3.8 Flash","provider":"google","input_price_per_million":79,"output_price_per_million":394,"context_length":1000000,"description":"Google's newest Gemini Flash model, with a 1M token context window.","capabilities":{"category":"chat","code":true,"is_new":true,"max_output_tokens":65536,"reasoning":true,"released_at":"2026-09-05","series":"gemini-flash","streaming":true,"tools":true,"vision":true},"created_at":"2026-09-05T17:38:51.975513+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":79,"retail_out":394,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gemini-embedding-001","display_name":"Gemini Embedding 001","provider":"google","input_price_per_million":2,"output_price_per_million":0,"context_length":2048,"description":"Google high-dimensional embedding model optimized for semantic search and Retrieval-Augmented Generation (RAG).","capabilities":{"category":"embedding","is_new":false,"released_at":"2024-05-14","series":"google-embedding","streaming":false},"created_at":"2026-08-15T14:19:17.65584+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":2,"retail_out":0,"context_len":2048,"data_retention":"allow","status":"enabled"}]},{"model_id":"gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B","provider":"cloudflare","input_price_per_million":10,"output_price_per_million":30,"context_length":256000,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":10,"retail_out":30,"context_len":256000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gemma-sea-lion-v4-27b-it","display_name":"Gemma SEA-LION v4 27B","provider":"cloudflare","input_price_per_million":35.1,"output_price_per_million":55.5,"context_length":128000,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":35.1,"retail_out":55.5,"context_len":128000,"data_retention":"allow","status":"enabled"}]},{"model_id":"glm-4.7-flash","display_name":"GLM 4.7 Flash","provider":"cloudflare","input_price_per_million":6.05,"output_price_per_million":40,"context_length":131072,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":6.05,"retail_out":40,"context_len":131072,"data_retention":"allow","status":"enabled"}]},{"model_id":"glm-5.2","display_name":"GLM-5.2","provider":"together","input_price_per_million":140,"output_price_per_million":440,"context_length":1048575,"description":"Zhipu GLM-5.2 with a 1M context window, strong Chinese and English coding.","capabilities":{"category":"chat","code":true,"is_new":false,"reasoning":true},"created_at":"2026-08-27T03:35:56.740915+00:00","providers":[{"provider":"together","display_name":"Together AI","country":"US","retail_in":147,"retail_out":462,"context_len":1048575,"data_retention":"allow","status":"enabled"},{"provider":"zai","display_name":"Z.ai","country":"CN","retail_in":140,"retail_out":440,"context_len":1000000,"data_retention":"allow","status":"enabled"},{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":140,"retail_out":440,"context_len":262144,"data_retention":"allow","status":"enabled"}]},{"model_id":"glm-5.3","display_name":"GLM 5.3","provider":"cloudflare","input_price_per_million":140,"output_price_per_million":440,"context_length":1310720,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"zai","display_name":"Z.ai","country":"CN","retail_in":140,"retail_out":440,"context_len":1000000,"data_retention":"allow","status":"enabled"},{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":140,"retail_out":440,"context_len":1310720,"data_retention":"allow","status":"enabled"}]},{"model_id":"glm-5.3-flash","display_name":"GLM 5.3 Flash","provider":"cloudflare","input_price_per_million":15,"output_price_per_million":50,"context_length":1310720,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":15,"retail_out":50,"context_len":1310720,"data_retention":"allow","status":"enabled"}]},{"model_id":"gpt-5.4-mini","display_name":"GPT-5.4 Mini","provider":"openai","input_price_per_million":79,"output_price_per_million":473,"context_length":400000,"description":"Strong mini model for coding, computer use, and sub-agents","capabilities":{"category":"chat","is_new":false,"vision":true},"created_at":"2026-04-07T15:08:22.809409+00:00","providers":[{"provider":"openai","display_name":"OpenAI","country":"US","retail_in":79,"retail_out":473,"context_len":400000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gpt-5.4-nano","display_name":"GPT-5.4 Nano","provider":"openai","input_price_per_million":21,"output_price_per_million":131,"context_length":400000,"description":"Cheapest GPT-5.4-class model for simple high-volume tasks","capabilities":{"category":"chat","is_new":false,"vision":true},"created_at":"2026-04-07T15:08:22.809409+00:00","providers":[{"provider":"openai","display_name":"OpenAI","country":"US","retail_in":21,"retail_out":131,"context_len":400000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gpt-5.6-luna","display_name":"GPT-5.6 Luna","provider":"openai","input_price_per_million":21,"output_price_per_million":126,"context_length":1050000,"description":"OpenAI most economical GPT-5.6 model, built for efficient high-volume workloads, with vision and a 1.05M context window.","capabilities":{"category":"chat","code":true,"is_new":false,"long_context":{"input_multiplier":2,"output_multiplier":1.5,"threshold_input_tokens":272000},"max_output_tokens":128000,"reasoning":true,"released_at":"2026-07-09","series":"gpt-5.6","streaming":true,"tools":true,"vision":true},"created_at":"2026-08-05T11:58:35.545864+00:00","providers":[{"provider":"openai","display_name":"OpenAI","country":"US","retail_in":21,"retail_out":126,"context_len":1050000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gpt-5.6-sol","display_name":"GPT-5.6 Sol","provider":"openai","input_price_per_million":525,"output_price_per_million":3150,"context_length":1050000,"description":"OpenAI frontier model for complex professional work, with maximum reasoning, vision, and a 1.05M context window.","capabilities":{"category":"chat","code":true,"is_new":false,"long_context":{"input_multiplier":2,"output_multiplier":1.5,"threshold_input_tokens":272000},"max_output_tokens":128000,"reasoning":true,"released_at":"2026-07-09","series":"gpt-5.6","streaming":true,"tools":true,"vision":true},"created_at":"2026-08-05T11:58:35.545864+00:00","providers":[{"provider":"openai","display_name":"OpenAI","country":"US","retail_in":525,"retail_out":3150,"context_len":1050000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gpt-5.6-terra","display_name":"GPT-5.6 Terra","provider":"openai","input_price_per_million":210,"output_price_per_million":1260,"context_length":1050000,"description":"OpenAI mid tier of the GPT-5.6 family, balancing intelligence and cost with vision, tool calling, and a 1.05M context window.","capabilities":{"category":"chat","code":true,"is_new":false,"long_context":{"input_multiplier":2,"output_multiplier":1.5,"threshold_input_tokens":272000},"max_output_tokens":128000,"reasoning":true,"released_at":"2026-07-09","series":"gpt-5.6","streaming":true,"tools":true,"vision":true},"created_at":"2026-08-05T11:58:35.545864+00:00","providers":[{"provider":"openai","display_name":"OpenAI","country":"US","retail_in":210,"retail_out":1260,"context_len":1050000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gpt-oss-120b","display_name":"GPT-OSS 120B","provider":"deepinfra","input_price_per_million":3.7,"output_price_per_million":17,"context_length":131072,"description":"OpenAI open-weight 120B, strong general reasoning at a fraction of hosted GPT pricing.","capabilities":{"category":"chat","code":true,"is_new":false,"public_price_provenance":{"deepinfra":{"model_id":"gpt-oss-120b","observed_at":"2026-08-31","policy":"provider_public_list","rates":{"input":3.7,"output":17},"release":"20260831131000","scope":"standard_uncached_text","source_commit":"c31b33b912630034c46f31e5a9b685557ebd47a6","source_url":"https://api.deepinfra.com/models/list","unit":"cents_per_million_tokens","upstream_model":"openai/gpt-oss-120b"}},"reasoning":true},"created_at":"2026-08-27T03:35:56.740915+00:00","providers":[{"provider":"together","display_name":"Together AI","country":"US","retail_in":16,"retail_out":63,"context_len":131072,"data_retention":"allow","status":"enabled"},{"provider":"deepinfra","display_name":"DeepInfra","country":"US","retail_in":3.7,"retail_out":17,"context_len":131072,"quantization":"bfloat16","data_retention":"allow","status":"enabled"},{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":35,"retail_out":75,"context_len":128000,"data_retention":"allow","status":"enabled"}]},{"model_id":"gpt-oss-20b","display_name":"GPT-OSS 20B","provider":"deepinfra","input_price_per_million":4,"output_price_per_million":15,"context_length":131072,"description":"OpenAI open-weight 20B, the cheapest capable chat model in the catalog.","capabilities":{"category":"chat","code":true,"is_new":false,"reasoning":true},"created_at":"2026-08-27T03:35:56.740915+00:00","providers":[{"provider":"together","display_name":"Together AI","country":"US","retail_in":6,"retail_out":21,"context_len":131072,"data_retention":"allow","status":"enabled"},{"provider":"deepinfra","display_name":"DeepInfra","country":"US","retail_in":4,"retail_out":15,"context_len":131072,"quantization":"bfloat16","data_retention":"allow","status":"enabled"},{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":20,"retail_out":30,"context_len":128000,"data_retention":"allow","status":"enabled"}]},{"model_id":"granite-4.0-h-micro","display_name":"Granite 4.0 H Micro","provider":"cloudflare","input_price_per_million":1.7,"output_price_per_million":11.2,"context_length":131000,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":1.7,"retail_out":11.2,"context_len":131000,"data_retention":"allow","status":"enabled"}]},{"model_id":"grok-4.20","display_name":"Grok 4.20","provider":"xai","input_price_per_million":210,"output_price_per_million":630,"context_length":2000000,"description":"xAI flagship reasoning model with 2M context","capabilities":{"category":"chat","is_new":false,"reasoning":true,"vision":true},"created_at":"2026-04-07T16:21:45.019705+00:00","providers":[{"provider":"xai","display_name":"xAI","country":"US","retail_in":210,"retail_out":630,"context_len":2000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"grok-4.3","display_name":"Grok 4.3","provider":"xai","input_price_per_million":131,"output_price_per_million":263,"context_length":1000000,"description":"xAI flagship reasoning model - 1M context, text+image (replaces grok-4.1-fast)","capabilities":{"category":"chat","code":true,"is_new":false,"reasoning":true,"vision":true},"created_at":"2026-06-07T11:59:41.837554+00:00","providers":[{"provider":"xai","display_name":"xAI","country":"US","retail_in":131,"retail_out":263,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"hy3","display_name":"Tencent HY3","provider":"deepinfra","input_price_per_million":14,"output_price_per_million":58,"context_length":262144,"capabilities":{"catalog_release":"20260911043000","category":"chat","is_new":false,"max_output_tokens":8192,"release_state":"beta_enabled"},"created_at":"2026-09-13T12:27:45.289043+00:00","providers":[{"provider":"deepinfra","display_name":"DeepInfra","country":"US","retail_in":14,"retail_out":58,"context_len":262144,"data_retention":"allow","status":"enabled"}]},{"model_id":"kimi-k2.6","display_name":"Kimi K2.6","provider":"cloudflare","input_price_per_million":95,"output_price_per_million":400,"context_length":262144,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":95,"retail_out":400,"context_len":262144,"data_retention":"allow","status":"enabled"}]},{"model_id":"kimi-k2.7-code","display_name":"Kimi K2.7 Code","provider":"together","input_price_per_million":95,"output_price_per_million":400,"context_length":262144,"description":"Moonshot Kimi K2.7 Code, coding-focused with a 256K context window.","capabilities":{"category":"chat","code":true,"is_new":false,"reasoning":true},"created_at":"2026-08-27T03:35:56.740915+00:00","providers":[{"provider":"together","display_name":"Together AI","country":"US","retail_in":100,"retail_out":420,"context_len":262144,"data_retention":"allow","status":"enabled"},{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":95,"retail_out":400,"context_len":262144,"data_retention":"allow","status":"enabled"}]},{"model_id":"kimi-k3","display_name":"Kimi K3","provider":"alibaba","input_price_per_million":300,"output_price_per_million":1500,"context_length":1048576,"capabilities":{"catalog_release":"20260909110000","category":"chat","is_new":false,"max_output_tokens":1048576},"created_at":"2026-09-09T18:55:49.796202+00:00","providers":[{"provider":"alibaba","display_name":"Alibaba Cloud","deployment":{"id":"alibaba-intl-kimi-k3","endpoint_region":"Singapore","inference_scope":"multi_region","inference_region":"International","source_url":"https://www.alibabacloud.com/help/en/model-studio/regions","verified_at":"2026-09-11T00:00:00Z","expires_at":"2026-12-10T00:00:00Z"},"country":"SG","retail_in":300,"retail_out":1500,"context_len":1048576,"data_retention":"allow","status":"enabled"}]},{"model_id":"llama-3.1-8b","display_name":"Llama 3.1 8B","provider":"cloudflare","input_price_per_million":15.2,"output_price_per_million":28.7,"context_length":32000,"capabilities":{"catalog_release":"20260907195500","catalog_route_release":"20260907220122","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-03-21T02:36:15.98025+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":15.2,"retail_out":28.7,"context_len":32000,"data_retention":"allow","status":"enabled"}]},{"model_id":"llama-3.2-1b-instruct","display_name":"Llama 3.2 1B Instruct","provider":"cloudflare","input_price_per_million":2.7,"output_price_per_million":20.1,"context_length":60000,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":2.7,"retail_out":20.1,"context_len":60000,"data_retention":"allow","status":"enabled"}]},{"model_id":"llama-3.2-3b-instruct","display_name":"Llama 3.2 3B Instruct","provider":"cloudflare","input_price_per_million":5.09,"output_price_per_million":33.5,"context_length":80000,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":5.09,"retail_out":33.5,"context_len":80000,"data_retention":"allow","status":"enabled"}]},{"model_id":"llama-3.3-70b","display_name":"Llama 3.3 70B","provider":"cloudflare","input_price_per_million":29.3,"output_price_per_million":225.3,"context_length":24000,"capabilities":{"catalog_release":"20260907195500","catalog_route_release":"20260907220122","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-03-21T02:36:15.98025+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":29.3,"retail_out":225.3,"context_len":24000,"data_retention":"allow","status":"enabled"}]},{"model_id":"mimo-v2.5","display_name":"Xiaomi MiMo V2.5","provider":"deepinfra","input_price_per_million":14,"output_price_per_million":28,"context_length":262144,"capabilities":{"catalog_release":"20260911043000","category":"chat","is_new":false,"max_output_tokens":8192,"release_state":"beta_enabled"},"created_at":"2026-09-13T12:27:45.289043+00:00","providers":[{"provider":"deepinfra","display_name":"DeepInfra","country":"US","retail_in":14,"retail_out":28,"context_len":262144,"data_retention":"allow","status":"enabled"}]},{"model_id":"minimax-m2.7","display_name":"MiniMax M2.7","provider":"minimax","input_price_per_million":30,"output_price_per_million":120,"context_length":204800,"capabilities":{"catalog_release":"20260911040000","category":"chat","is_new":false,"max_output_tokens":8192,"release_state":"beta_acceptance"},"created_at":"2026-09-13T12:27:44.80011+00:00","providers":[{"provider":"minimax","display_name":"MiniMax","country":"SG","retail_in":30,"retail_out":120,"context_len":204800,"data_retention":"allow","status":"enabled"}]},{"model_id":"mistral-small-3.1-24b-instruct","display_name":"Mistral Small 3.1 24B","provider":"cloudflare","input_price_per_million":35.1,"output_price_per_million":55.5,"context_length":128000,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":35.1,"retail_out":55.5,"context_len":128000,"data_retention":"allow","status":"enabled"}]},{"model_id":"nano-banana-2","display_name":"Nano Banana 2","provider":"google","input_price_per_million":53,"output_price_per_million":6300,"context_length":32768,"description":"Google mid-tier image-output Gemini model. Supports 0.5K/1K/2K/4K output resolutions (this catalog offering exposes up to 2K; see spec for 4K rationale).","capabilities":{"access_policy":"balance","api_endpoint":"/v1/images/generations","category":"image","is_new":false,"max_image_size":"2K","pricing_unit":"per_image_variable","released_at":"2026-07-01","series":"nano-banana"},"created_at":"2026-08-21T08:03:16.002634+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":53,"retail_out":6300,"context_len":32768,"data_retention":"allow","status":"enabled"}]},{"model_id":"nano-banana-2-lite","display_name":"Nano Banana 2 Lite","provider":"google","input_price_per_million":26,"output_price_per_million":3150,"context_length":32768,"description":"Google fast, low-cost image-output Gemini model. Output fixed at 1K resolution.","capabilities":{"access_policy":"balance","api_endpoint":"/v1/images/generations","category":"image","is_new":false,"max_image_size":"1K","pricing_unit":"per_image_variable","released_at":"2026-07-01","series":"nano-banana"},"created_at":"2026-08-21T08:03:16.002634+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":26,"retail_out":3150,"context_len":32768,"data_retention":"allow","status":"enabled"}]},{"model_id":"nano-banana-pro","display_name":"Nano Banana Pro","provider":"google","input_price_per_million":210,"output_price_per_million":12600,"context_length":32768,"description":"Google premium image-output Gemini model. 1K and 2K are priced identically; this catalog offering exposes up to 2K.","capabilities":{"access_policy":"balance","api_endpoint":"/v1/images/generations","category":"image","is_new":false,"max_image_size":"2K","pricing_unit":"per_image_variable","released_at":"2026-07-01","series":"nano-banana"},"created_at":"2026-08-21T08:03:16.002634+00:00","providers":[{"provider":"google","display_name":"Google","country":"US","retail_in":210,"retail_out":12600,"context_len":32768,"data_retention":"allow","status":"enabled"}]},{"model_id":"nemotron-3-120b-a12b","display_name":"Nemotron 3 120B A12B","provider":"cloudflare","input_price_per_million":50,"output_price_per_million":150,"context_length":256000,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":50,"retail_out":150,"context_len":256000,"data_retention":"allow","status":"enabled"}]},{"model_id":"nemotron-3-ultra-550b-a55b","display_name":"NVIDIA Nemotron 3 Ultra","provider":"deepinfra","input_price_per_million":50,"output_price_per_million":220,"context_length":262144,"capabilities":{"catalog_release":"20260911043000","category":"chat","is_new":false,"max_output_tokens":8192,"release_state":"beta_enabled"},"created_at":"2026-09-13T12:27:45.289043+00:00","providers":[{"provider":"deepinfra","display_name":"DeepInfra","country":"US","retail_in":50,"retail_out":220,"context_len":262144,"data_retention":"allow","status":"enabled"}]},{"model_id":"qwen2.5-coder-32b-instruct","display_name":"Qwen2.5 Coder 32B","provider":"cloudflare","input_price_per_million":66,"output_price_per_million":100,"context_length":32768,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":66,"retail_out":100,"context_len":32768,"data_retention":"allow","status":"enabled"}]},{"model_id":"qwen3-30b-a3b-fp8","display_name":"Qwen3 30B A3B FP8","provider":"cloudflare","input_price_per_million":5.09,"output_price_per_million":33.5,"context_length":32768,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":5.09,"retail_out":33.5,"context_len":32768,"data_retention":"allow","status":"enabled"}]},{"model_id":"qwen3-embedding-0.6b","display_name":"Qwen3 Embedding 0.6B","provider":"cloudflare","input_price_per_million":1.18,"output_price_per_million":0,"context_length":8192,"capabilities":{"catalog_release":"20260907195500","category":"embedding","embedding_dims":1024,"is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":1.18,"retail_out":0,"context_len":8192,"data_retention":"allow","status":"enabled"}]},{"model_id":"qwen3-embedding-4b","display_name":"Qwen3 Embedding 4B","provider":"dos-ai","input_price_per_million":2,"output_price_per_million":0,"context_length":32768,"description":"Self-hosted multilingual text embedding (2560 dims), strong on Vietnamese. Priced at our OpenRouter fallback cost.","capabilities":{"category":"embedding","embedding_dims":2560,"is_new":false},"created_at":"2026-08-04T10:46:40.973061+00:00","providers":[]},{"model_id":"qwen3.7-max","display_name":"Qwen 3.7 Max","provider":"qwen","input_price_per_million":263,"output_price_per_million":788,"context_length":1000000,"description":"Qwen 3.7 Max tier - 1M context (standard price; OpenRouter shows a 50%-off promo)","capabilities":{"category":"chat","code":true,"is_new":false,"reasoning":true},"created_at":"2026-06-07T11:59:41.837554+00:00","providers":[{"provider":"qwen","display_name":"Alibaba Cloud (Qwen)","country":"SG","retail_in":263,"retail_out":788,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"qwen3.7-plus","display_name":"Qwen 3.7 Plus","provider":"qwen","input_price_per_million":42,"output_price_per_million":168,"context_length":1000000,"description":"Qwen 3.7 Plus - multimodal (text+image), 1M context","capabilities":{"category":"chat","code":true,"is_new":false,"reasoning":true,"vision":true},"created_at":"2026-06-07T11:59:41.837554+00:00","providers":[{"provider":"qwen","display_name":"Alibaba Cloud (Qwen)","country":"SG","retail_in":42,"retail_out":168,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"qwen3.8-27b","display_name":"Qwen3.8-27B","provider":"dos-ai","input_price_per_million":11.25,"output_price_per_million":150,"context_length":262144,"description":"DOS.AI hosted Qwen3.8-27B for reasoning, coding, tool use, and multilingual text generation.","capabilities":{"agent_free":true,"category":"chat","code":true,"is_featured":true,"is_new":false,"parameters":"27B Dense","reasoning":true,"streaming":true,"tools":true,"vision":true},"created_at":"2026-03-21T02:36:15.98025+00:00","providers":[{"provider":"dos-ai","display_name":"DOS.AI","country":"VN","retail_in":11.25,"retail_out":150,"context_len":262144,"quantization":"nvfp4","data_retention":"allow","status":"enabled"},{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":45,"retail_out":320,"context_len":262144,"data_retention":"allow","status":"enabled"},{"provider":"alibaba","display_name":"Alibaba Cloud","country":"SG","retail_in":50,"retail_out":300,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"qwen3.8-flash","display_name":"Qwen3.8 Flash","provider":"alibaba","input_price_per_million":15,"output_price_per_million":47,"context_length":1000000,"capabilities":{"catalog_release":"20260908044236","category":"chat","is_new":false,"max_output_tokens":131072},"created_at":"2026-09-08T07:19:46.920451+00:00","providers":[{"provider":"alibaba","display_name":"Alibaba Cloud","country":"SG","retail_in":15,"retail_out":47,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"qwen3.8-max","display_name":"Qwen 3.8 Max","provider":"qwen","input_price_per_million":187,"output_price_per_million":562,"context_length":1000000,"description":"Qwen 3.8 Max - Alibaba's 2.4T-parameter MoE flagship, 1M context, multimodal input (text+image+video)","capabilities":{"category":"chat","code":true,"is_new":false,"max_output_tokens":131072,"reasoning":true,"released_at":"2026-08-03","series":"qwen-max","streaming":true,"tools":true,"vision":true},"created_at":"2026-08-19T03:05:28.140855+00:00","providers":[{"provider":"qwen","display_name":"Alibaba Cloud (Qwen)","country":"SG","retail_in":187,"retail_out":562,"context_len":1000000,"data_retention":"allow","status":"enabled"}]},{"model_id":"qwq-32b","display_name":"QwQ 32B","provider":"cloudflare","input_price_per_million":66,"output_price_per_million":100,"context_length":24000,"capabilities":{"catalog_release":"20260907195500","category":"chat","is_new":false,"release_state":"beta_enabled"},"created_at":"2026-09-08T07:19:44.448853+00:00","providers":[{"provider":"cloudflare","display_name":"Cloudflare","country":"US","retail_in":66,"retail_out":100,"context_len":24000,"data_retention":"allow","status":"enabled"}]},{"model_id":"wan2.2-t2i-flash","display_name":"Wan 2.2 T2I Flash","provider":"alibaba","input_price_per_million":2625,"output_price_per_million":0,"description":"Alibaba DashScope fast text-to-image model (Wanx family). Submit+poll upstream, existing generateDashScopeImage pipeline, now reachable from the public /v1/images/generations route.","capabilities":{"access_policy":"balance","api_endpoint":"/v1/images/generations","category":"image","is_new":false,"pricing_unit":"per_image","released_at":"2026-01-01","series":"wanx"},"created_at":"2026-08-02T01:59:30.7559+00:00","providers":[{"provider":"alibaba","display_name":"Alibaba Cloud","country":"SG","retail_in":2625,"retail_out":0,"data_retention":"allow","status":"enabled"}]},{"model_id":"wan2.7-i2v","display_name":"Wan 2.7 Image-to-Video","provider":"alibaba","input_price_per_million":10000,"output_price_per_million":0,"description":"Video generation from image + text prompt via Alibaba Wan 2.7. Pricing: per 1000 seconds.","capabilities":{"access_policy":"balance","api_endpoint":"/v1/videos/generations","category":"video","is_new":false,"pricing_unit":"thousand_seconds","request_kind":"video_image","video_output":true},"created_at":"2026-04-06T18:15:39.910202+00:00","providers":[{"provider":"alibaba","display_name":"Alibaba Cloud","country":"SG","retail_in":10000,"retail_out":0,"data_retention":"allow","status":"enabled"}]},{"model_id":"wan2.7-t2v","display_name":"Wan 2.7 Text-to-Video","provider":"alibaba","input_price_per_million":10000,"output_price_per_million":0,"description":"Video generation from text prompt via Alibaba Wan 2.7. Duration 2-15s, 1080P, native audio. Pricing: per 1000 seconds.","capabilities":{"access_policy":"balance","api_endpoint":"/v1/videos/generations","category":"video","is_new":false,"pricing_unit":"thousand_seconds","request_kind":"video_text","video_output":true},"created_at":"2026-04-06T18:15:39.910202+00:00","providers":[{"provider":"alibaba","display_name":"Alibaba Cloud","country":"SG","retail_in":10000,"retail_out":0,"data_retention":"allow","status":"enabled"}]}]}