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?Source
tev1-4b-experimental 2 sourcesTogether AI––0.0420free0.031532,768–officialofficial-together
gpt-image-1.5Together AI–––0.03400.0340––officialofficial-together
meta-llama/Meta-Llama-3.1-8B-InstructDeepInfra––0.03000.05000.0350131,072–aggregatorlitellm
Llama 3.2 3B Instruct 2 sourcesNovita AI––0.03000.05000.0350131,072llama3aggregatorlitellm
qwen-image-20Together AI–––0.03500.0350––officialofficial-together
seedream-50-liteTogether AI–––0.03500.0350––officialofficial-together
gpt-oss-20bDarkbloomfp8–0.01800.09000.0360131,072o200kapiopenrouter
gpt-oss-20bAkashMLfp4–0.01800.09000.0360131,072o200kapiopenrouter
meta-llama/Meta-Llama-3-8B-InstructDeepInfra––0.03000.06000.03758,192–aggregatorlitellm
Qwen3 Reranker 8BNovita AI––0.0500free0.037532,768–aggregatormodelsdev
Extractscaledown promo −20%––0.0500free0.03751,000,000–apiopenrouter
Summarizescaledown promo −20%––0.0500free0.03751,000,000–apiopenrouter
gemini-flash-image-2-5Together AI–––0.03900.0390––officialofficial-together
Ministral 3B 2 sourcesAzure AI Foundry––0.04000.04000.0400128,000–aggregatorlitellm
Prompt Guard 2 86M 2 sourcesGroq––0.04000.04000.0400512–aggregatorlitellm
Voxtral Mini 3B 2507 2 sourcesAWS Bedrock––0.04000.04000.040032,768–aggregatorlitellm
Llama 3 8B Instruct 2 sourcesNovita AI––0.04000.04000.04008,192–aggregatorlitellm
Gemma 4 E4B IT 2 sourcesDeepInfra––0.02000.1000.0400131,072–aggregatorlitellm
flux-1-kontext-proTogether AI––0.0400–0.0400––officialofficial-together
flux1-1-proTogether AI––0.0400–0.0400––officialofficial-together
Granite 4.0 MicroCloudflare Workers AI––0.01700.1120.0408131,000–apiopenrouter
Llama 3 8B LunarisOpenRouter––0.04000.05000.04258,192llama3apiopenrouter
Llama 3 8B LunarisParasail––0.04000.05000.04258,192llama3apiopenrouter
Llama 3 8B LunarisDeepInfrafp8+turbo–0.04000.05000.04258,192llama3apiopenrouter
Sao10K/L3-8B-Lunaris-v1-TurboDeepInfra––0.04000.05000.04258,192–aggregatorlitellm
Gemma 3 4BParasail––0.04000.05000.0425131,072geminiapiopenrouter
Nex-N2.5-MiniOpenRouter––0.02500.1000.0438262,144qwen2apiopenrouter
Nex-N2.5-MiniNex AGI––0.02500.1000.0438262,144qwen2apiopenrouter
gpt-oss-120bPrime Intellectfp4–0.03500.07500.0450131,072o200kapiopenrouter
gpt-oss-20bDeepInfraflex–0.02400.1120.0460131,072o200kapiopenrouter
gemini-31-flash-imageTogether AI–––0.04660.0466––officialofficial-together
Llama 3.2 11b Vision InstructDeepInfra––0.04900.04900.0490131,072–aggregatorlitellm
Gemma 3 4B 2 sourcesAWS Bedrock––0.04000.08000.0500131,072geminiaggregatorlitellm
Sao10k L3 8B Lunaris 2 sourcesNovita AI––0.05000.05000.05008,192–aggregatorlitellm
L3 8B Stheno V3.2 2 sourcesNovita AI––0.05000.05000.05008,192–aggregatorlitellm
Gemma 4 E2B IT 2 sourcesAWS Bedrock––0.04000.08000.0500128,000–aggregatorlitellm
Rerank 5 ProCohere––0.0500–0.0500––officialofficial-cohere
Gemma 3 4BDeepInfraflex–0.04000.08000.0500131,072geminiapiopenrouter
Gemma 4 26B A4BPrime Intellect––0.03400.1010.0508262,144gemmaapiopenrouter
Nemotron 3.5 Lightning 30B A3BPerplexity––0.01150.1700.0511262,144–aggregatorlitellm
Gemma 3 4BAWS Bedrock–ap-southeast-20.04120.08240.0515131,072geminiaggregatorlitellm
LFM2-24B-A2BTogether AI––0.03000.1200.052532,768–aggregatormodelsdev
Qwen3-Embedding-8BNovita AI––0.0700free0.052540,960–aggregatormodelsdev
gpt-image-2Together AI–––0.05300.0530––officialofficial-together
Qwen3.7 FlashOpenRouter––0.03000.1300.05501,000,000qwen2apiopenrouter
Qwen3.7 Flash 2 sourcesAlibaba Cloud––0.03000.1300.05501,000,000qwen2apiopenrouter
gpt-oss-20bCoreWeavefp4–0.03000.1300.0550131,072o200kapiopenrouter
Qwen2.5 7B InstructDeepInfra––0.04000.1000.055032,768–aggregatorlitellm
llama-guard-3-8bDeepInfra––0.05500.05500.0550131,072–aggregatorlitellm
gpt-oss-20bDekaLLM––0.02900.1400.0568131,072o200kapiopenrouter

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