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 ↑?Cache readCache writeContextTokenizerConfidence?
Command R7BCohere––0.03750.1500.0656––––official
Gemma 4 26B A4BDarkbloom––0.04000.1500.06750.0100–262,144gemmaapi
gpt-oss-120bDekaLLM––0.03000.1800.06750.0300–131,072o200kapi
gpt-oss-20b 2 sourcesNovita AI––0.04000.1500.0675––131,072o200kaggregator
DeepSeek R1 0528 Qwen3 8B 2 sourcesNovita AI––0.06000.09000.0675––128,000–aggregator
Ling 3.1 FlashOpenRouter––0.04500.1350.06750.009000–1,000,000–api
GPT-5 nanoOpenAIflex–0.02500.2000.06880.002500–400,000o200kapi
gemini-31-flash-lite-imageTogether AI–––0.06900.0690––––official
gpt-oss-120bAkashMLfp4–0.03000.1870.06930.0300–131,072o200kapi
nvidia/NVIDIA-Nemotron-Nano-9B-v2DeepInfra––0.04000.1600.0700––131,072–aggregator
Baichuan M2 32B 2 sourcesNovita AI––0.07000.07000.0700––131,072–aggregator
Qwen2.5 7B Instruct 2 sourcesNovita AI––0.07000.07000.0700––32,768–aggregator
flux-2-maxTogether AI––0.0700–0.0700––––official
Phi-4DeepInfraflex–0.05600.1120.0700––16,384–api
gpt-oss-120b 3 sourcesDeepInfra––0.03700.1700.07030.0185–131,072o200kapi
Llama 3.2 1B InstructOpenRouter––0.02700.2010.0705––60,000llama3api
Llama 3.2 1B InstructCloudflare Workers AI––0.02700.2010.0705––60,000llama3api
arcee-ai/trinity-miniTogether AI––0.04500.1500.0713––128,000–aggregator
DeepSeek-V4-Flash-0731DeepInfraflex+fp8–0.04800.1440.07200.0120–1,048,576–api
Mistral Nemo 2 sourcesNovita AI––0.04000.1700.0725––131,072mistralaggregator
Amazon Nova MicroAWS Bedrock–us-gov-west-10.04200.1680.07350.0105–128,000–aggregator
Gemma 3 12BOpenRouter––0.05000.1500.0750––131,072geminiapi
gpt-oss-20bSiliconFlowfp8–0.04000.1800.0750––131,072o200kapi
Gemma 3 12B 4 sourcesDeepInfra––0.05000.1500.0750––131,072geminiofficial
text-embedding-ada-002Azure AI Foundry––0.100free0.0750––8,192–aggregator
Embed v3 MultilingualAzure AI Foundry––0.100free0.0750––512–aggregator
Embed v3 EnglishAzure AI Foundry––0.100free0.0750––512–aggregator
Mistral EmbedMistral AI––0.100free0.0750––8,000–aggregator
text-embedding-ada-002OpenAI––0.100free0.0750––8,192–aggregator
qwen-image-20-proTogether AI–––0.07500.0750––––official
Gemma 3 4BAWS Bedrock–eu-west-20.06000.1200.0750––131,072geminiaggregator
Hy-MT2-1.8BOpenRouter––0.04400.1770.0773––8,192–api
Hy-MT2-1.8BTencent Cloudfp8–0.04400.1770.0773––8,192–api
GLM 5.3 FlashWafernvfp4us0.04200.1840.07750.0410–1,048,576–api
DeepSeek V4.1 Flash 1017SAIL Researchfp4us0.07000.1000.07750.007000–1,048,576deepseekapi
Embed 5 FastCohere––0.0800–0.0800––––official
flux-1-kontext-maxTogether AI––0.0800–0.0800––––official
Gemma 3 27BDeepInfraflex+fp8–0.06400.1280.0800––131,072geminiapi
Amazon Nova MicroAWS Bedrock–eu0.04600.1840.08050.0115–128,000–aggregator
Granite 4.2 8BOpenRouter––0.06000.1500.08250.0150–131,072–api
Granite 4.2 8BCoreWeave––0.06000.1500.08250.0150–131,072–api
NVIDIA-Nemotron-3.5-Lightning 2 sourcesDeepInfra––0.06000.1600.08500.0300–262,144–official
DeepSeek V4.1 Flash 1017particle-aiflexus0.03000.2500.08500.005000–1,048,576deepseekapi
Mistral Small 3.2 24BDeepInfraflex+fp8–0.06000.1600.0850––256,000mistralapi
Particle-1particle-aiflexus0.03000.2500.08500.001500–1,048,576–api
Solar Mini 4OpenRouter––0.05000.2000.08750.005000–524,288–api
Phi-4OpenRouter––0.07000.1400.0875––16,384–api
MythoMax 13BOpenRouter––0.08000.1100.0875––8,192–api
DeepSeek V4 Flash 0731Relacefp4–0.07000.1400.08750.0140–1,048,576deepseekapi
Nemotron 3 Nano 30B A3BNovita AIfp4–0.05000.2000.0875––262,144–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