Offerings

Every active offering: a model as served by one host, with its current canonical price. Sort by clicking a column header; filter with the row below. Prices are USD per 1M tokens unless the unit toggle is set to per 1M characters (an approximation using a measured, blended tokens-per-character ratio).

Showing tier-tagged and vendor-direct models. Show all offerings, including the long tail

More columns: - Vendor + Region + Cache - Batch - Tokenizer + Last change - Source All columns Default columns

ModelVendorHostVariantRegionInputOutputBlended ↑?Batch inBatch outContextTokenizerConfidence?Source
Llama 3.3 70B Instruct 2 sourcesMetaDeepInfra––0.2300.4000.273––128,000llama3aggregatorlitellm
Grok 4 FastxAIAzure AI Foundry––0.2000.5000.275––2,000,000–aggregatorlitellm
Llama 3.3 70B InstructMetaAkashMLfp8–0.2000.5200.280––128,000llama3apiopenrouter
Llama 4 Scout 3 sourcesMetaNovita AI––0.1800.5900.283––10,000,000llama3apiopenrouter
Llama 4 ScoutMetaTogether AI––0.1800.5900.283––10,000,000llama3aggregatorlitellm
Mistral Small 4Mistral AIMistral AI–eu0.1650.6600.289––262,144mistralapiopenrouter
Mistral Small 4Mistral AIMistral AI–us0.1650.6600.289––262,144mistralapiopenrouter
Llama 3.3 70B InstructMetaParasailfp8–0.2200.5000.290––128,000llama3apiopenrouter
DeepSeek V4 FlashDeepSeekAzure AI Foundry–us0.2100.5600.298––1,048,576deepseekapiopenrouter
Qwen3-235B-A22B 2 sourcesAlibaba CloudNebius AI Studio––0.2000.6000.300––131,072qwen2aggregatorlitellm
Codestral 25.01Mistral AIGoogle Vertex AI––0.2000.6000.300––262,144mistralaggregatorlitellm
Llama 4 MaverickMetaDigitalOcean––0.1880.6530.304––1,000,000llama3apiopenrouter
Gemini 2.5 Flash-LiteGoogleGooglepriority–0.1800.7200.315––1,048,576geminiapiopenrouter
DeepSeek V3.2 (chat)DeepSeekDeepSeek––0.2800.4200.315––128,000deepseekaggregatorlitellm
DeepSeek V3.2 (reasoner)DeepSeekDeepSeek––0.2800.4200.315––128,000deepseekaggregatorlitellm
GPT-5 miniOpenAIOpenAIflex–0.1251.000.344––400,000o200kapiopenrouter
Llama 4 Scout 2 sourcesMetaAzure AI Foundry––0.2000.7800.345––10,000,000llama3aggregatorlitellm
Llama 4 Maverick 2 sourcesMetaDeepInfra––0.2000.8000.350––1,000,000llama3aggregatorlitellm
Qwen3-235B-A22B 2 sourcesAlibaba CloudNovita AI––0.2000.8000.350––131,072qwen2aggregatorlitellm
Llama 4 ScoutMetaGoogle Vertex AI–us-east50.2500.7000.363––10,000,000llama3apiopenrouter
Llama 4 Scout 2 sourcesMetaGoogle Vertex AI––0.2500.7000.3630.1250.35010,000,000llama3aggregatorlitellm
DeepSeek V3.2 (chat)DeepSeekDeepInfraflex+fp4–0.2560.7120.370––128,000deepseekapiopenrouter
Qwen3-235B-A22BAlibaba CloudFireworks AI––0.2200.8800.385––131,072qwen2aggregatorlitellm
GPT-6 Luna 2 sourcesOpenAIOpenAIfast–0.2001.000.400––1,050,000o200kofficialofficial-openai
DeepSeek V3.2 (reasoner)DeepSeekHyperbolic––0.4000.4000.400––128,000deepseekaggregatorlitellm
Llama 4 Maverick 2 sourcesMetaNovita AI––0.2700.8500.415––1,000,000llama3aggregatorlitellm
Gemini 2.5 FlashGoogleGoogleflex–0.1501.250.425––1,048,576geminiapiopenrouter
DeepSeek V3.2 (chat) 2 sourcesDeepSeekDeepInfra––0.2500.9500.425––128,000deepseekaggregatorlitellm
Llama 4 Maverick 2 sourcesMetaAzure AI Foundry––0.2501.000.438––1,000,000llama3aggregatorlitellm
Codestral 25.01 2 sourcesMistral AIAzure AI Foundry––0.3000.9000.450––262,144mistralaggregatorlitellm
Codestral 25.01Mistral AIMistral AI––0.3000.9000.450––262,144mistralaggregatormodelsdev
DeepSeek V3.2 (chat)DeepSeekOpenRouter––0.2571.030.450––128,000deepseekapiopenrouter
DeepSeek V3.2 (chat)DeepSeekDeepInfrafp4–0.3200.8900.463––128,000deepseekapiopenrouter
DeepSeek V4 FlashDeepSeekWafermxfp4–0.6000.1700.493––1,048,576deepseekapiopenrouter
DeepSeek V3.2 (chat)DeepSeekStreamLake promo −10%––0.2861.140.500––128,000deepseekapiopenrouter
Grok 3 minixAIAzure AI Foundry––0.2501.270.505––131,072–aggregatorlitellm
Llama 4 MaverickMetaOpenRouter––0.3501.000.513––1,000,000llama3apiopenrouter
Llama 4 MaverickMetaParasailfp8–0.3501.000.513––1,000,000llama3apiopenrouter
Llama 4 MaverickMetaGoogle Vertex AI–us-east50.3501.150.550––1,000,000llama3apiopenrouter
Llama 4 Maverick 2 sourcesMetaGoogle Vertex AI––0.3501.150.5500.1750.5751,000,000llama3aggregatorlitellm
Qwen3-Coder-480B-A35BAlibaba CloudGoogle Vertex AI––0.2201.800.6150.1100.900262,144qwen2aggregatorlitellm
Inkling SmallThinking MachinesOpenRouter––0.4501.200.638––524,288–apiopenrouter
Inkling SmallThinking MachinesDeepInfrafp8–0.4501.200.638––524,288–apiopenrouter
Inkling Small 2 sourcesThinking MachinesDeepInfra––0.4501.200.638––524,288–aggregatorlitellm
Inkling SmallThinking MachinesDeepInfrafp4–0.4501.200.638––524,288–apiopenrouter
Llama 3.3 70B Instruct 2 sourcesMetaGroq––0.5900.7900.640––128,000llama3apiopenrouter
Qwen3-Coder-480B-A35B 2 sourcesAlibaba CloudNovita AI––0.3801.550.673––262,144qwen2aggregatorlitellm
GPT-5 miniOpenAIOpenRouter––0.2502.000.688––400,000o200kapiopenrouter
GPT-5 mini 3 sourcesOpenAIAzure AI Foundry––0.2502.000.6880.1251.00400,000o200kapiopenrouter
GPT-5 mini 3 sourcesOpenAIOpenAI––0.2502.000.6880.1251.00400,000o200kapiopenrouter

Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence