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 every active offering, including the long tail. Show curated models only

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

ModelHostVariantRegionInputOutputBlended ↑?Batch inBatch outContextTokenizerConfidence?Source
Gemini 2.5 Flash-LiteGoogleflex–0.05000.2000.0875––1,048,576geminiapiopenrouter
Phi-4 3 sourcesDeepInfra––0.07000.1400.0875––16,384–officialofficial-deepinfra
MythoMax 13BParasail––0.08000.1100.0875––8,192–apiopenrouter
Qwen Turbo 2 sourcesAlibaba Cloud––0.05000.2000.0875––129,024–aggregatorlitellm
qwen-turbo-latestAlibaba Cloud––0.05000.2000.0875––1,000,000–aggregatorlitellm
Nemotron 3.5 Lightning 30B A3B 2 sourcesFireworks AI––0.05000.2000.0875––262,144–aggregatorlitellm
Nemotron 3 Nano 30B A3B 2 sourcesNovita AI––0.05000.2000.0875––262,144–aggregatorlitellm
Nemotron 3 Nano 30B A3B 2 sourcesDeepInfra––0.05000.2000.0875––262,144–aggregatorlitellm
gpt-oss-20bTogether AI––0.05000.2000.0875––131,072o200kaggregatorlitellm
MiniMax M3.1 FlashTenstorrentfp8–0.05000.2000.0875––1,048,576–apiopenrouter
Ling 3.0 Flash VLDeepInfra––0.06000.1800.0900––131,072–apiopenrouter
Ling 3.0 Flash FinDeepInfrafp4–0.06000.1800.0900––262,144–apiopenrouter
Ling 3.0 Flash 3 sourcesNovita AI promo −65%––0.06000.1800.0900––262,144–apiopenrouter
Ling 3.0 Flash 2 sourcesDeepInfra––0.06000.1800.0900––262,144–apiopenrouter
gpt-oss-20b 2 sourcesAWS Bedrock–eu-west-10.07000.1500.0900––131,072o200kapiopenrouter
gpt-oss-20b 3 sourcesAWS Bedrock––0.07000.1500.09000.03500.150131,072o200kapiopenrouter
MythoMax 13B 2 sourcesNovita AI––0.09000.09000.0900––8,192–aggregatorlitellm
inclusionai/ling-3.0-flash-fastNovita AI––0.06000.1800.0900––262,144–aggregatorlitellm
Embed v4Azure AI Foundry––0.120free0.0900––128,000–aggregatormodelsdev
DeepSeek-V4-Flash-0731DeepInfra––0.06000.1800.0900––1,048,576–officialofficial-deepinfra
DeepSeek-V4-Flash-0731DeepInfrafp8–0.06000.1800.0900––1,048,576–apiopenrouter
Ling 3.0 Flash VLDeepInfrafp4–0.06000.1800.0900––131,072–apiopenrouter
Qwen3.5-9BDeepInfraflex–0.08000.1200.0900––262,144qwen2apiopenrouter
Ling 3.0 FlashDeepInfrafp4–0.06000.1800.0900––262,144–apiopenrouter
DeepSeek V4 FlashDeepInfraflex+fp8–0.07200.1440.0900––1,048,576deepseekapiopenrouter
Qwen3.5-9BDarkbloomfp4–0.08000.1300.0925––262,144qwen2apiopenrouter
Ternary Bonsai 2 9BDarkbloomint4–0.08000.1300.0925––262,144qwen2apiopenrouter
Ternary Bonsai 2 9BOpenRouter––0.08000.1300.0925––262,144qwen2apiopenrouter
Gemma 3 12BNextBitint4–0.07500.1500.0938––131,072geminiapiopenrouter
GLM 5.3 FlashDarkbloomfp4–0.06500.1800.0938––1,048,576–apiopenrouter
Gemma 3 4BDeepInfrapriority–0.07500.1500.0938––131,072geminiapiopenrouter
Schematron V2 SmallOpenRouter––0.05000.2300.0950––128,000–apiopenrouter
Schematron V2 SmallInference.net––0.05000.2300.0950––128,000–apiopenrouter
Qwen2.5 32B InstructNebius AI Studio––0.06000.2000.0950––128,000–aggregatorlitellm
Schematron V2 SmallInference.net–us0.05000.2300.0950––128,000–apiopenrouter
text-embedding-3-largeAzure AI Foundry––0.130free0.0975––8,191–aggregatormodelsdev
text-embedding-3-largeOpenAI––0.130free0.0975––8,191–aggregatormodelsdev
Reka EdgeOpenRouter––0.1000.1000.100––16,384–apiopenrouter
Ministral 3 3B 2512OpenRouter––0.1000.1000.100––131,072mistralapiopenrouter
GPT-6 Luna ProOpenAIflex–0.05000.2500.100––1,050,000o200kapiopenrouter
GPT-6 Luna 2 sourcesOpenAIflex–0.05000.2500.100––1,050,000o200kofficialofficial-openai
Reka EdgeReka AI––0.1000.1000.100––16,384–apiopenrouter
Ministral 3 3B 2512Mistral AIzdr–0.1000.1000.100––131,072mistralapiopenrouter
Ministral 3 3B 2512 3 sourcesMistral AI––0.1000.1000.100––131,072mistralapiopenrouter
gpt-oss-120bCrusoe––0.05000.2500.100––131,072o200kapiopenrouter
Gemma 3 27BDeepInfrafp8–0.08000.1600.100––131,072geminiapiopenrouter
FW-Nemotron-Lightning-3.5-30B-A3BAzure AI Foundry––0.06000.2200.100––262,144–aggregatorlitellm
llama3.1-8bCerebras––0.1000.1000.100––128,000–aggregatorlitellm
Gemma 3 27B 3 sourcesDeepInfra––0.08000.1600.100––131,072geminiofficialofficial-deepinfra
eu.meta.llama3-2-1b-instruct-v1:0AWS Bedrock––0.1000.1000.100––128,000–aggregatorlitellm

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