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 ↑?ContextLast changeConfidence?
Amazon Nova Micro 2 sourcesAWS Bedrock––0.03500.1400.0613128,000–aggregator
Amazon Nova MicroAmazon––0.03500.1400.0613128,000–aggregator
Amazon Nova MicroAWS Bedrock–us0.03500.1400.0613128,000–aggregator
Amazon Nova MicroAWS Bedrock–apac0.03700.1480.0648128,000–aggregator
GPT-5 nanoOpenAIflex–0.02500.2000.0688400,000–api
Phi-4DeepInfraflex–0.05600.1120.070016,384–api
Amazon Nova MicroAWS Bedrock–us-gov-west-10.04200.1680.0735128,000–aggregator
Amazon Nova MicroAWS Bedrock–eu0.04600.1840.0805128,000–aggregator
Phi-4OpenRouter––0.07000.1400.087516,384–api
Gemini 2.5 Flash-LiteGoogleflex–0.05000.2000.08751,048,576–api
Phi-4 3 sourcesDeepInfra––0.07000.1400.087516,384–official
DeepSeek V4 FlashDeepInfraflex+fp8–0.07200.1440.09001,048,576–api
GPT-6 Luna 2 sourcesOpenAIflex–0.05000.2500.1001,050,000–official
MiniMax-M1Fireworks AI––0.1000.1000.1001,000,000–aggregator
GPT-6 LunaOpenAIbatch–0.05000.2500.1001,050,000–official
Amazon Nova Lite 2 sourcesAWS Bedrock––0.06000.2400.105300,000–aggregator
Amazon Nova LiteAmazon––0.06000.2400.105300,000–aggregator
Amazon Nova LiteAWS Bedrock–us0.06000.2400.105300,000–aggregator
Amazon Nova LiteAWS Bedrock–apac0.06300.2520.110300,000–aggregator
DeepSeek V4 FlashOpenRouter––0.09000.1800.1131,048,576–api
DeepSeek V4 FlashDeepInfrafp8–0.09000.1800.1131,048,576–api
DeepSeek V4 Flash 2 sourcesDeepInfra––0.09000.1800.1131,048,576–aggregator
Llama 4 ScoutDeepInfraflex+fp8–0.08000.2400.12010,000,000–api
DeepSeek V4 FlashDigitalOcean––0.09800.1960.1231,048,576–api
Amazon Nova LiteAWS Bedrock–us-gov-west-10.07200.2880.126300,000–aggregator
DeepSeek V4 Flash 2 sourcesFireworks AI––0.1050.2100.1311,048,576–api
Amazon Nova LiteAWS Bedrock–eu0.07800.3120.137300,000–aggregator
GPT-5 nanoOpenRouter––0.05000.4000.138400,000–api
GPT-5 nano 3 sourcesAzure AI Foundry––0.05000.4000.138400,000–api
GPT-5 nano 3 sourcesOpenAI––0.05000.4000.138400,000–api
GPT-5 nanoPerplexity––0.05000.4000.138400,000–aggregator
Llama 4 ScoutOpenRouter––0.1000.3000.15010,000,000–api
DeepSeek V4 FlashRelacefp4–0.05000.4500.1501,048,5762026-11-11 ↑api
Llama 4 ScoutDeepInfrafp8–0.1000.3000.15010,000,000–api
Mistral Small 3.1 2 sourcesAzure AI Foundry––0.1000.3000.150131,0722026-03-03 ↓aggregator
Llama 4 Scout 2 sourcesDeepInfra––0.1000.3000.15010,000,0002026-08-27 ↑aggregator
Mistral Small 3.1 2 sourcesGoogle Vertex AI––0.1000.3000.150131,0722026-09-11 ↓aggregator
GPT-5 nanoAzure AI Foundry–swedencentral0.05500.4400.151400,000–api
GPT-5 nanoAzure AI Foundry–eu0.05500.4400.151400,000–aggregator
GPT-5 nanoAzure AI Foundry–us0.05500.4400.151400,000–aggregator
Llama 3.3 70B InstructDeepInfrafp8+turbo–0.1000.3200.155128,000–api
Llama 3.3 70B InstructHyperbolic––0.1200.3000.165128,000–aggregator
DeepSeek V4 FlashSiliconFlowfp8–0.1300.2800.1681,048,576–api
DeepSeek V4 FlashDeepInfrafp8+priority–0.1350.2700.1691,048,576–api
DeepSeek V4 FlashVenice promo −30%––0.1380.2750.1721,048,576–api
Gemini 2.5 Flash-LiteOpenRouter––0.1000.4000.1751,048,576–api
DeepSeek V4 FlashStreamLake promo −41%fp8–0.1400.2800.1751,048,576–api
DeepSeek V4 FlashGMI Cloud promo −35%fp8–0.1400.2800.1751,048,576–api
DeepSeek V4 FlashBaidufp8–0.1400.2800.1751,048,576–api
DeepSeek V4 FlashAtlas Cloudfp4–0.1400.2800.1751,048,576–api

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