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 ↑?ContextTokenizerConfidence?
Gemini 2.5 Flash-LiteGoogleflex–0.05000.2000.08751,048,576geminiapi
Phi-4 3 sourcesDeepInfra––0.07000.1400.087516,384–official
MythoMax 13BParasail––0.08000.1100.08758,192–api
Qwen Turbo 2 sourcesAlibaba Cloud––0.05000.2000.0875129,024–aggregator
qwen-turbo-latestAlibaba Cloud––0.05000.2000.08751,000,000–aggregator
Nemotron 3.5 Lightning 30B A3B 2 sourcesFireworks AI––0.05000.2000.0875262,144–aggregator
Nemotron 3 Nano 30B A3B 2 sourcesNovita AI––0.05000.2000.0875262,144–aggregator
Nemotron 3 Nano 30B A3B 2 sourcesDeepInfra––0.05000.2000.0875262,144–aggregator
gpt-oss-20bTogether AI––0.05000.2000.0875131,072o200kaggregator
MiniMax M3.1 FlashTenstorrentfp8–0.05000.2000.08751,048,576–api
Ling 3.0 Flash VLDeepInfra––0.06000.1800.0900131,072–api
Ling 3.0 Flash FinDeepInfrafp4–0.06000.1800.0900262,144–api
Ling 3.0 Flash 3 sourcesNovita AI promo −65%––0.06000.1800.0900262,144–api
Ling 3.0 Flash 2 sourcesDeepInfra––0.06000.1800.0900262,144–api
gpt-oss-20b 2 sourcesAWS Bedrock–eu-west-10.07000.1500.0900131,072o200kapi
gpt-oss-20b 3 sourcesAWS Bedrock––0.07000.1500.0900131,072o200kapi
MythoMax 13B 2 sourcesNovita AI––0.09000.09000.09008,192–aggregator
inclusionai/ling-3.0-flash-fastNovita AI––0.06000.1800.0900262,144–aggregator
Embed v4Azure AI Foundry––0.120free0.0900128,000–aggregator
DeepSeek-V4-Flash-0731DeepInfra––0.06000.1800.09001,048,576–official
DeepSeek-V4-Flash-0731DeepInfrafp8–0.06000.1800.09001,048,576–api
Ling 3.0 Flash VLDeepInfrafp4–0.06000.1800.0900131,072–api
Qwen3.5-9BDeepInfraflex–0.08000.1200.0900262,144qwen2api
Ling 3.0 FlashDeepInfrafp4–0.06000.1800.0900262,144–api
DeepSeek V4 FlashDeepInfraflex+fp8–0.07200.1440.09001,048,576deepseekapi
Qwen3.5-9BDarkbloomfp4–0.08000.1300.0925262,144qwen2api
Ternary Bonsai 2 9BDarkbloomint4–0.08000.1300.0925262,144qwen2api
Ternary Bonsai 2 9BOpenRouter––0.08000.1300.0925262,144qwen2api
Gemma 3 12BNextBitint4–0.07500.1500.0938131,072geminiapi
GLM 5.3 FlashDarkbloomfp4–0.06500.1800.09381,048,576–api
Gemma 3 4BDeepInfrapriority–0.07500.1500.0938131,072geminiapi
Schematron V2 SmallOpenRouter––0.05000.2300.0950128,000–api
Schematron V2 SmallInference.net––0.05000.2300.0950128,000–api
Qwen2.5 32B InstructNebius AI Studio––0.06000.2000.0950128,000–aggregator
Schematron V2 SmallInference.net–us0.05000.2300.0950128,000–api
text-embedding-3-largeAzure AI Foundry––0.130free0.09758,191–aggregator
text-embedding-3-largeOpenAI––0.130free0.09758,191–aggregator
Reka EdgeOpenRouter––0.1000.1000.10016,384–api
Ministral 3 3B 2512OpenRouter––0.1000.1000.100131,072mistralapi
GPT-6 Luna ProOpenAIflex–0.05000.2500.1001,050,000o200kapi
GPT-6 Luna 2 sourcesOpenAIflex–0.05000.2500.1001,050,000o200kofficial
Reka EdgeReka AI––0.1000.1000.10016,384–api
Ministral 3 3B 2512Mistral AIzdr–0.1000.1000.100131,072mistralapi
Ministral 3 3B 2512 3 sourcesMistral AI––0.1000.1000.100131,072mistralapi
gpt-oss-120bCrusoe––0.05000.2500.100131,072o200kapi
Gemma 3 27BDeepInfrafp8–0.08000.1600.100131,072geminiapi
FW-Nemotron-Lightning-3.5-30B-A3BAzure AI Foundry––0.06000.2200.100262,144–aggregator
llama3.1-8bCerebras––0.1000.1000.100128,000–aggregator
Gemma 3 27B 3 sourcesDeepInfra––0.08000.1600.100131,072geminiofficial
eu.meta.llama3-2-1b-instruct-v1:0AWS Bedrock––0.1000.1000.100128,000–aggregator

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