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 ↑?Cache readCache writeBatch inBatch outContextConfidence?Source
Amazon Nova Micro 2 sourcesAmazonAWS Bedrock––0.03500.1400.06130.0087500.03500.01750.0700128,000aggregatorlitellm
Amazon Nova MicroAmazonAmazon––0.03500.1400.0613––––128,000aggregatorlitellm
Amazon Nova MicroAmazonAWS Bedrock–us0.03500.1400.06130.008750–0.01750.0700128,000aggregatorlitellm
Amazon Nova MicroAmazonAWS Bedrock–apac0.03700.1480.06480.009250–––128,000aggregatorlitellm
GPT-5 nanoOpenAIOpenAIflex–0.02500.2000.06880.002500–––400,000apiopenrouter
Phi-4MicrosoftDeepInfraflex–0.05600.1120.0700––––16,384apiopenrouter
Amazon Nova MicroAmazonAWS Bedrock–us-gov-west-10.04200.1680.07350.0105–0.02100.0840128,000aggregatorlitellm
Amazon Nova MicroAmazonAWS Bedrock–eu0.04600.1840.08050.0115–––128,000aggregatorlitellm
Phi-4MicrosoftOpenRouter––0.07000.1400.0875––––16,384apiopenrouter
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
DeepSeek V4 FlashDeepSeekDeepInfraflex+fp8–0.07200.1440.09000.0144–––1,048,576apiopenrouter
GPT-6 Luna 2 sourcesOpenAIOpenAIflex–0.05000.2500.1000.0050000.0625––1,050,000officialofficial-openai
MiniMax-M1MiniMaxFireworks AI––0.1000.1000.100––––1,000,000aggregatorlitellm
GPT-6 LunaOpenAIOpenAIbatch–0.05000.2500.1000.0050000.0625––1,050,000officialofficial-openai
Amazon Nova Lite 2 sourcesAmazonAWS Bedrock––0.06000.2400.1050.01500.06000.03000.120300,000aggregatorlitellm
Amazon Nova LiteAmazonAmazon––0.06000.2400.105––––300,000aggregatorlitellm
Amazon Nova LiteAmazonAWS Bedrock–us0.06000.2400.1050.0150–0.03000.120300,000aggregatorlitellm
Amazon Nova LiteAmazonAWS Bedrock–apac0.06300.2520.1100.0158–––300,000aggregatorlitellm
DeepSeek V4 FlashDeepSeekOpenRouter––0.09000.1800.1130.0180–––1,048,576apiopenrouter
DeepSeek V4 FlashDeepSeekDeepInfrafp8–0.09000.1800.1130.0180–––1,048,576apiopenrouter
DeepSeek V4 Flash 2 sourcesDeepSeekDeepInfra––0.09000.1800.1130.01800.113––1,048,576aggregatorlitellm
Llama 4 ScoutMetaDeepInfraflex+fp8–0.08000.2400.120––––10,000,000apiopenrouter
DeepSeek V4 FlashDeepSeekDigitalOcean––0.09800.1960.1230.0196–––1,048,576apiopenrouter
Amazon Nova LiteAmazonAWS Bedrock–us-gov-west-10.07200.2880.1260.0180–0.03600.144300,000aggregatorlitellm
DeepSeek V4 Flash 2 sourcesDeepSeekFireworks AI––0.1050.2100.1310.0210–––1,048,576apiopenrouter
Amazon Nova LiteAmazonAWS Bedrock–eu0.07800.3120.1370.0195–––300,000aggregatorlitellm
GPT-5 nanoOpenAIOpenRouter––0.05000.4000.1380.005000–––400,000apiopenrouter
GPT-5 nano 3 sourcesOpenAIAzure AI Foundry––0.05000.4000.1380.0100–0.02500.200400,000apiopenrouter
GPT-5 nano 3 sourcesOpenAIOpenAI––0.05000.4000.1380.005000–0.02500.200400,000apiopenrouter
GPT-5 nanoOpenAIPerplexity––0.05000.4000.1380.005000–––400,000aggregatorlitellm
Llama 4 ScoutMetaOpenRouter––0.1000.3000.150––––10,000,000apiopenrouter
DeepSeek V4 FlashDeepSeekRelacefp4–0.05000.4500.1500.0500–––1,048,576apiopenrouter
Llama 4 ScoutMetaDeepInfrafp8–0.1000.3000.150––––10,000,000apiopenrouter
Mistral Small 3.1 2 sourcesMistral AIAzure AI Foundry––0.1000.3000.150––––131,072aggregatorlitellm
Llama 4 Scout 2 sourcesMetaDeepInfra––0.1000.3000.150––––10,000,000aggregatorlitellm
Mistral Small 3.1 2 sourcesMistral AIGoogle Vertex AI––0.1000.3000.150––––131,072aggregatorlitellm
GPT-5 nanoOpenAIAzure AI Foundry–swedencentral0.05500.4400.1510.0110–––400,000apiopenrouter
GPT-5 nanoOpenAIAzure AI Foundry–eu0.05500.4400.1510.005500–0.02750.220400,000aggregatorlitellm
GPT-5 nanoOpenAIAzure AI Foundry–us0.05500.4400.1510.005500–0.02750.220400,000aggregatorlitellm
Llama 3.3 70B InstructMetaDeepInfrafp8+turbo–0.1000.3200.155––––128,000apiopenrouter
Llama 3.3 70B InstructMetaHyperbolic––0.1200.3000.165––––128,000aggregatorlitellm
DeepSeek V4 FlashDeepSeekSiliconFlowfp8–0.1300.2800.1680.0280–––1,048,576apiopenrouter
DeepSeek V4 FlashDeepSeekDeepInfrafp8+priority–0.1350.2700.1690.0270–––1,048,576apiopenrouter
DeepSeek V4 FlashDeepSeekVenice promo −30%––0.1380.2750.1720.0280–––1,048,576apiopenrouter
Gemini 2.5 Flash-LiteGoogleOpenRouter––0.1000.4000.1750.01000.0833––1,048,576apiopenrouter
DeepSeek V4 FlashDeepSeekStreamLake promo −41%fp8–0.1400.2800.1750.0280–––1,048,576apiopenrouter
DeepSeek V4 FlashDeepSeekGMI Cloud promo −35%fp8–0.1400.2800.1750.0280–––1,048,576apiopenrouter
DeepSeek V4 FlashDeepSeekBaidufp8–0.1400.2800.1750.0280–––1,048,576apiopenrouter
DeepSeek V4 FlashDeepSeekAtlas Cloudfp4–0.1400.2800.1750.0280–––1,048,576apiopenrouter

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