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 outContextTokenizerConfidence?Source
Command R7BCohereCohere––0.03750.1500.0656––––––officialofficial-cohere
Gemma 4 26B A4BGoogleDarkbloom––0.04000.1500.06750.0100–––262,144gemmaapiopenrouter
gpt-oss-120bOpenAIDekaLLM––0.03000.1800.06750.0300–––131,072o200kapiopenrouter
gpt-oss-20b 2 sourcesOpenAINovita AI––0.04000.1500.0675––––131,072o200kaggregatorlitellm
DeepSeek R1 0528 Qwen3 8B 2 sourcesDeepSeekNovita AI––0.06000.09000.0675––––128,000–aggregatorlitellm
Ling 3.1 FlashOpenRouterOpenRouter––0.04500.1350.06750.009000–––1,000,000–apiopenrouter
GPT-5 nanoOpenAIOpenAIflex–0.02500.2000.06880.002500–––400,000o200kapiopenrouter
gemini-31-flash-lite-imageTogether AITogether AI–––0.06900.0690––––––officialofficial-together
gpt-oss-120bOpenAIAkashMLfp4–0.03000.1870.06930.0300–––131,072o200kapiopenrouter
nvidia/NVIDIA-Nemotron-Nano-9B-v2NVIDIADeepInfra––0.04000.1600.0700––––131,072–aggregatorlitellm
Baichuan M2 32B 2 sourcesNovita AINovita AI––0.07000.07000.0700––––131,072–aggregatorlitellm
Qwen2.5 7B Instruct 2 sourcesAlibaba CloudNovita AI––0.07000.07000.0700––––32,768–aggregatorlitellm
flux-2-maxTogether AITogether AI––0.0700–0.0700––––––officialofficial-together
Phi-4MicrosoftDeepInfraflex–0.05600.1120.0700––––16,384–apiopenrouter
gpt-oss-120b 3 sourcesOpenAIDeepInfra––0.03700.1700.07030.0185–––131,072o200kapiopenrouter
Llama 3.2 1B InstructMetaOpenRouter––0.02700.2010.0705––––60,000llama3apiopenrouter
Llama 3.2 1B InstructMetaCloudflare Workers AI––0.02700.2010.0705––––60,000llama3apiopenrouter
arcee-ai/trinity-miniTogether AITogether AI––0.04500.1500.0713––––128,000–aggregatorlitellm
DeepSeek-V4-Flash-0731DeepInfraDeepInfraflex+fp8–0.04800.1440.07200.0120–––1,048,576–apiopenrouter
Mistral Nemo 2 sourcesMistral AINovita AI––0.04000.1700.0725––––131,072mistralaggregatorlitellm
Amazon Nova MicroAmazonAWS Bedrock–us-gov-west-10.04200.1680.07350.0105–0.02100.0840128,000–aggregatorlitellm
Gemma 3 12BGoogleOpenRouter––0.05000.1500.0750––––131,072geminiapiopenrouter
gpt-oss-20bOpenAISiliconFlowfp8–0.04000.1800.0750––––131,072o200kapiopenrouter
Gemma 3 12B 4 sourcesGoogleDeepInfra––0.05000.1500.0750––––131,072geminiofficialofficial-deepinfra
text-embedding-ada-002OpenAIAzure AI Foundry––0.100free0.0750––––8,192–aggregatormodelsdev
Embed v3 MultilingualAzure AI FoundryAzure AI Foundry––0.100free0.0750––––512–aggregatormodelsdev
Embed v3 EnglishAzure AI FoundryAzure AI Foundry––0.100free0.0750––––512–aggregatormodelsdev
Mistral EmbedMistral AIMistral AI––0.100free0.0750––––8,000–aggregatormodelsdev
text-embedding-ada-002OpenAIOpenAI––0.100free0.0750––––8,192–aggregatormodelsdev
qwen-image-20-proTogether AITogether AI–––0.07500.0750––––––officialofficial-together
Gemma 3 4BGoogleAWS Bedrock–eu-west-20.06000.1200.0750––––131,072geminiaggregatorlitellm
Hy-MT2-1.8BOpenRouterOpenRouter––0.04400.1770.0773––––8,192–apiopenrouter
Hy-MT2-1.8BOpenRouterTencent Cloudfp8–0.04400.1770.0773––––8,192–apiopenrouter
GLM 5.3 FlashZhipu AI (Z.ai)Wafernvfp4us0.04200.1840.07750.0410–––1,048,576–apiopenrouter
DeepSeek V4.1 Flash 1017DeepSeekSAIL Researchfp4us0.07000.1000.07750.007000–––1,048,576deepseekapiopenrouter
Embed 5 FastCohereCohere––0.0800–0.0800––––––officialofficial-cohere
flux-1-kontext-maxTogether AITogether AI––0.0800–0.0800––––––officialofficial-together
Gemma 3 27BGoogleDeepInfraflex+fp8–0.06400.1280.0800––––131,072geminiapiopenrouter
Amazon Nova MicroAmazonAWS Bedrock–eu0.04600.1840.08050.0115–––128,000–aggregatorlitellm
Granite 4.2 8BOpenRouterOpenRouter––0.06000.1500.08250.0150–––131,072–apiopenrouter
Granite 4.2 8BOpenRouterCoreWeave––0.06000.1500.08250.0150–––131,072–apiopenrouter
NVIDIA-Nemotron-3.5-Lightning 2 sourcesNVIDIADeepInfra––0.06000.1600.08500.0300–––262,144–officialofficial-deepinfra
DeepSeek V4.1 Flash 1017DeepSeekparticle-aiflexus0.03000.2500.08500.005000–––1,048,576deepseekapiopenrouter
Mistral Small 3.2 24BMistral AIDeepInfraflex+fp8–0.06000.1600.0850––––256,000mistralapiopenrouter
Particle-1particle-aiparticle-aiflexus0.03000.2500.08500.001500–––1,048,576–apiopenrouter
Solar Mini 4OpenRouterOpenRouter––0.05000.2000.08750.005000–––524,288–apiopenrouter
Phi-4MicrosoftOpenRouter––0.07000.1400.0875––––16,384–apiopenrouter
MythoMax 13BOpenRouterOpenRouter––0.08000.1100.0875––––8,192–apiopenrouter
DeepSeek V4 Flash 0731DeepSeekRelacefp4–0.07000.1400.08750.0140–––1,048,576deepseekapiopenrouter
Nemotron 3 Nano 30B A3BNVIDIANovita AIfp4–0.05000.2000.0875––––262,144–apiopenrouter

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