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

ModelVendorHostVariantRegionInputOutputBlended ↑?Cache readCache writeBatch inBatch outContextConfidence?Source
Gemini 2.5 Flash-LiteGoogleGoogleflex–0.05000.2000.08750.0050000.0417––1,048,576apiopenrouter
Phi-4 3 sourcesMicrosoftDeepInfra––0.07000.1400.0875––––16,384officialofficial-deepinfra
MythoMax 13BOpenRouterParasail––0.08000.1100.0875––––8,192apiopenrouter
Qwen Turbo 2 sourcesAlibaba CloudAlibaba Cloud––0.05000.2000.0875––––129,024aggregatorlitellm
qwen-turbo-latestAlibaba CloudAlibaba Cloud––0.05000.2000.0875––––1,000,000aggregatorlitellm
Nemotron 3.5 Lightning 30B A3B 2 sourcesNVIDIAFireworks AI––0.05000.2000.08750.0100–––262,144aggregatorlitellm
Nemotron 3 Nano 30B A3B 2 sourcesNVIDIANovita AI––0.05000.2000.0875––––262,144aggregatorlitellm
Nemotron 3 Nano 30B A3B 2 sourcesNVIDIADeepInfra––0.05000.2000.08750.0250–––262,144aggregatorlitellm
gpt-oss-20bOpenAITogether AI––0.05000.2000.0875––––131,072aggregatorlitellm
MiniMax M3.1 FlashMiniMaxTenstorrentfp8–0.05000.2000.08750.005000–––1,048,576apiopenrouter
Ling 3.0 Flash VLOpenRouterDeepInfra––0.06000.1800.09000.0120–––131,072apiopenrouter
Ling 3.0 Flash FinOpenRouterDeepInfrafp4–0.06000.1800.09000.0120–––262,144apiopenrouter
Ling 3.0 Flash 3 sourcesOpenRouterNovita AI promo −65%––0.06000.1800.09000.0120–––262,144apiopenrouter
Ling 3.0 Flash 2 sourcesOpenRouterDeepInfra––0.06000.1800.09000.0120–––262,144apiopenrouter
gpt-oss-20b 2 sourcesOpenAIAWS Bedrock–eu-west-10.07000.1500.0900––––131,072apiopenrouter
gpt-oss-20b 3 sourcesOpenAIAWS Bedrock––0.07000.1500.0900––0.03500.150131,072apiopenrouter
MythoMax 13B 2 sourcesOpenRouterNovita AI––0.09000.09000.0900––––8,192aggregatorlitellm
inclusionai/ling-3.0-flash-fastNovita AINovita AI––0.06000.1800.09000.0120–––262,144aggregatorlitellm
Embed v4Azure AI FoundryAzure AI Foundry––0.120free0.0900––––128,000aggregatormodelsdev
DeepSeek-V4-Flash-0731DeepInfraDeepInfra––0.06000.1800.09000.0150–––1,048,576officialofficial-deepinfra
DeepSeek-V4-Flash-0731DeepInfraDeepInfrafp8–0.06000.1800.09000.0150–––1,048,576apiopenrouter
Ling 3.0 Flash VLOpenRouterDeepInfrafp4–0.06000.1800.09000.0120–––131,072apiopenrouter
Qwen3.5-9BAlibaba CloudDeepInfraflex–0.08000.1200.0900––––262,144apiopenrouter
Ling 3.0 FlashOpenRouterDeepInfrafp4–0.06000.1800.09000.0120–––262,144apiopenrouter
DeepSeek V4 FlashDeepSeekDeepInfraflex+fp8–0.07200.1440.09000.0144–––1,048,576apiopenrouter
Qwen3.5-9BAlibaba CloudDarkbloomfp4–0.08000.1300.09250.0400–––262,144apiopenrouter
Ternary Bonsai 2 9BDarkbloomDarkbloomint4–0.08000.1300.09250.0400–––262,144apiopenrouter
Ternary Bonsai 2 9BDarkbloomOpenRouter––0.08000.1300.09250.0400–––262,144apiopenrouter
Gemma 3 12BGoogleNextBitint4–0.07500.1500.09380.0500–––131,072apiopenrouter
GLM 5.3 FlashZhipu AI (Z.ai)Darkbloomfp4–0.06500.1800.09380.0120–––1,048,576apiopenrouter
Gemma 3 4BGoogleDeepInfrapriority–0.07500.1500.0938––––131,072apiopenrouter
Schematron V2 SmallOpenRouterOpenRouter––0.05000.2300.09500.0500–––128,000apiopenrouter
Schematron V2 SmallOpenRouterInference.net––0.05000.2300.09500.0500–––128,000apiopenrouter
Qwen2.5 32B InstructAlibaba CloudNebius AI Studio––0.06000.2000.0950––––128,000aggregatorlitellm
Schematron V2 SmallOpenRouterInference.net–us0.05000.2300.09500.0500–––128,000apiopenrouter
text-embedding-3-largeOpenAIAzure AI Foundry––0.130free0.0975––––8,191aggregatormodelsdev
text-embedding-3-largeOpenAIOpenAI––0.130free0.0975––––8,191aggregatormodelsdev
Reka EdgeOpenRouterOpenRouter––0.1000.1000.100––––16,384apiopenrouter
Ministral 3 3B 2512Mistral AIOpenRouter––0.1000.1000.1000.0100–––131,072apiopenrouter
GPT-6 Luna ProOpenAIOpenAIflex–0.05000.2500.1000.0050000.0625––1,050,000apiopenrouter
GPT-6 Luna 2 sourcesOpenAIOpenAIflex–0.05000.2500.1000.0050000.0625––1,050,000officialofficial-openai
Reka EdgeOpenRouterReka AI––0.1000.1000.100––––16,384apiopenrouter
Ministral 3 3B 2512Mistral AIMistral AIzdr–0.1000.1000.1000.0100–––131,072apiopenrouter
Ministral 3 3B 2512 3 sourcesMistral AIMistral AI––0.1000.1000.1000.0100–––131,072apiopenrouter
gpt-oss-120bOpenAICrusoe––0.05000.2500.1000.0500–––131,072apiopenrouter
Gemma 3 27BGoogleDeepInfrafp8–0.08000.1600.100––––131,072apiopenrouter
FW-Nemotron-Lightning-3.5-30B-A3BAzure AI FoundryAzure AI Foundry––0.06000.2200.1000.0100–––262,144aggregatorlitellm
llama3.1-8bMetaCerebras––0.1000.1000.100––––128,000aggregatorlitellm
Gemma 3 27B 3 sourcesGoogleDeepInfra––0.08000.1600.100––––131,072officialofficial-deepinfra
eu.meta.llama3-2-1b-instruct-v1:0MetaAWS Bedrock––0.1000.1000.100––––128,000aggregatorlitellm

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