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

ModelHostVariantRegionInputOutputBlended ↑?Batch inBatch outContextTokenizerLast changeConfidence?Source
Llama 3.3 70B Instruct 2 sourcesDeepInfra––0.2300.4000.273––128,000llama32026-08-27 ↓aggregatorlitellm
Grok 4 FastAzure AI Foundry––0.2000.5000.275––2,000,000–2026-01-14 ↓aggregatorlitellm
Llama 3.3 70B InstructAkashMLfp8–0.2000.5200.280––128,000llama3–apiopenrouter
Llama 4 Scout 3 sourcesNovita AI––0.1800.5900.283––10,000,000llama32026-01-13 ↓apiopenrouter
Llama 4 ScoutTogether AI––0.1800.5900.283––10,000,000llama3–aggregatorlitellm
Mistral Small 4Mistral AI–eu0.1650.6600.289––262,144mistral–apiopenrouter
Mistral Small 4Mistral AI–us0.1650.6600.289––262,144mistral–apiopenrouter
Llama 3.3 70B InstructParasailfp8–0.2200.5000.290––128,000llama3–apiopenrouter
DeepSeek V4 FlashAzure AI Foundry–us0.2100.5600.298––1,048,576deepseek–apiopenrouter
Qwen3-235B-A22B 2 sourcesNebius AI Studio––0.2000.6000.300––131,072qwen2–aggregatorlitellm
Codestral 25.01Google Vertex AI––0.2000.6000.300––262,144mistral–aggregatorlitellm
Llama 4 MaverickDigitalOcean––0.1880.6530.304––1,000,000llama3–apiopenrouter
Gemini 2.5 Flash-LiteGooglepriority–0.1800.7200.315––1,048,576gemini–apiopenrouter
DeepSeek V3.2 (chat)DeepSeek––0.2800.4200.315––128,000deepseek2026-01-13 ↓aggregatorlitellm
DeepSeek V3.2 (reasoner)DeepSeek––0.2800.4200.315––128,000deepseek2026-01-13 ↓aggregatorlitellm
GPT-5 miniOpenAIflex–0.1251.000.344––400,000o200k–apiopenrouter
Llama 4 Scout 2 sourcesAzure AI Foundry––0.2000.7800.345––10,000,000llama3–aggregatorlitellm
Llama 4 Maverick 2 sourcesDeepInfra––0.2000.8000.350––1,000,000llama32026-08-27 ↑aggregatorlitellm
Qwen3-235B-A22B 2 sourcesNovita AI––0.2000.8000.350––131,072qwen22026-01-13 ↓aggregatorlitellm
Llama 4 ScoutGoogle Vertex AI–us-east50.2500.7000.363––10,000,000llama3–apiopenrouter
Llama 4 Scout 2 sourcesGoogle Vertex AI––0.2500.7000.3630.1250.35010,000,000llama3–aggregatorlitellm
DeepSeek V3.2 (chat)DeepInfraflex+fp4–0.2560.7120.370––128,000deepseek–apiopenrouter
Qwen3-235B-A22BFireworks AI––0.2200.8800.385––131,072qwen2–aggregatorlitellm
GPT-6 Luna 2 sourcesOpenAIfast–0.2001.000.400––1,050,000o200k–officialofficial-openai
DeepSeek V3.2 (reasoner)Hyperbolic––0.4000.4000.400––128,000deepseek–aggregatorlitellm
Llama 4 Maverick 2 sourcesNovita AI––0.2700.8500.415––1,000,000llama32026-01-13 ↓aggregatorlitellm
Gemini 2.5 FlashGoogleflex–0.1501.250.425––1,048,576gemini–apiopenrouter
DeepSeek V3.2 (chat) 2 sourcesDeepInfra––0.2500.9500.425––128,000deepseek2026-08-27 ↓aggregatorlitellm
Llama 4 Maverick 2 sourcesAzure AI Foundry––0.2501.000.438––1,000,000llama32026-09-17 ↕aggregatorlitellm
Codestral 25.01 2 sourcesAzure AI Foundry––0.3000.9000.450––262,144mistral–aggregatorlitellm
Codestral 25.01Mistral AI––0.3000.9000.450––262,144mistral2026-08-21 ↓aggregatormodelsdev
DeepSeek V3.2 (chat)OpenRouter––0.2571.030.450––128,000deepseek–apiopenrouter
DeepSeek V3.2 (chat)DeepInfrafp4–0.3200.8900.463––128,000deepseek–apiopenrouter
DeepSeek V4 FlashWafermxfp4–0.6000.1700.493––1,048,576deepseek2026-10-27 ↓apiopenrouter
DeepSeek V3.2 (chat)StreamLake promo −10%––0.2861.140.500––128,000deepseek–apiopenrouter
Grok 3 miniAzure AI Foundry––0.2501.270.505––131,072–2026-01-14 ↓aggregatorlitellm
Llama 4 MaverickOpenRouter––0.3501.000.513––1,000,000llama3–apiopenrouter
Llama 4 MaverickParasailfp8–0.3501.000.513––1,000,000llama3–apiopenrouter
Llama 4 MaverickGoogle Vertex AI–us-east50.3501.150.550––1,000,000llama3–apiopenrouter
Llama 4 Maverick 2 sourcesGoogle Vertex AI––0.3501.150.5500.1750.5751,000,000llama3–aggregatorlitellm
Qwen3-Coder-480B-A35BGoogle Vertex AI––0.2201.800.6150.1100.900262,144qwen22026-08-21 ↓aggregatorlitellm
Inkling SmallOpenRouter––0.4501.200.638––524,288––apiopenrouter
Inkling SmallDeepInfrafp8–0.4501.200.638––524,288––apiopenrouter
Inkling Small 2 sourcesDeepInfra––0.4501.200.638––524,288––aggregatorlitellm
Inkling SmallDeepInfrafp4–0.4501.200.638––524,288––apiopenrouter
Llama 3.3 70B Instruct 2 sourcesGroq––0.5900.7900.640––128,000llama3–apiopenrouter
Qwen3-Coder-480B-A35B 2 sourcesNovita AI––0.3801.550.673––262,144qwen22026-08-27 ↑aggregatorlitellm
GPT-5 miniOpenRouter––0.2502.000.688––400,000o200k–apiopenrouter
GPT-5 mini 3 sourcesAzure AI Foundry––0.2502.000.6880.1251.00400,000o200k–apiopenrouter
GPT-5 mini 3 sourcesOpenAI––0.2502.000.6880.1251.00400,000o200k–apiopenrouter

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