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?Source
accounts/fireworks/models/flux-1-dev-controlnet-unionFireworks AI––0.0010000.0010000.001000––4,096–aggregatorlitellm
juggernaut-lightning-fluxTogether AI–––0.0017000.001700––––officialofficial-together
sd-xlTogether AI–––0.0019000.001900––––officialofficial-together
p-image-ideogramTogether AI–––0.0022500.002250––––officialofficial-together
juggernaut-pro-fluxTogether AI–––0.0049000.004900––––officialofficial-together
Qwen ImageTogether AI–––0.0058000.005800––––officialofficial-together
Qwen3-Embedding-8BNebius AI Studio––0.0100free0.007500––40,960–aggregatormodelsdev
BGE M3Novita AI––0.0100free0.007500––8,192–aggregatormodelsdev
BGE Reranker V2 M3Novita AI––0.0100free0.007500––8,000–aggregatormodelsdev
Qwen/Qwen2.5-Coder-7BNebius AI Studio––0.01000.03000.0150––32,768–aggregatorlitellm
text-embedding-3-smallAzure AI Foundry––0.0200free0.0150––8,191–aggregatormodelsdev
text-embedding-3-smallOpenAI––0.0200free0.0150––8,191–aggregatormodelsdev
flux-2-devTogether AI–––0.01540.0154––––officialofficial-together
eu.meta.llama3-2-3b-instruct-v1:0Lambda discontinued––0.01500.02500.0175––128,000–aggregatorlitellm
bytedance-seedream-3-0Together AI–––0.01800.0180––––officialofficial-together
Llama 3.2 3B InstructDeepInfra––0.02000.02000.0200––131,072llama3aggregatorlitellm
PaddleOCR VL 2 sourcesNovita AI––0.02000.02000.0200––16,384–aggregatorlitellm
Llama 3.2 1B Instruct 2 sourcesNovita AI––0.02000.02000.0200––60,000llama3aggregatorlitellm
Qwen/Qwen2-1.5B-InstructTogether AI––0.02000.02000.0200––32,768–aggregatorlitellm
Rerank 5 FastCohere––0.0200–0.0200––––officialofficial-cohere
Mistral NemoDekaLLMfp8–0.01800.03000.0210––131,072mistralapiopenrouter
gpt-oss-20bPrime Intellectfp4–0.02000.03000.02250.0180–131,072o200kapiopenrouter
Ling 3.0 Tinyant-digitalfp8–0.01500.04500.02250.003000–262,144–apiopenrouter
Ling 3.0 TinyOpenRouter––0.01500.04500.02250.003000–262,144–apiopenrouter
Mistral Nemoio.net promo −28%––0.02300.03000.02480.0150–131,072mistralapiopenrouter
Llama 3.1 8B InstructOpenRouter––0.02000.04000.0250––131,072llama3apiopenrouter
Llama 3.1 8B InstructDeepInfrafp8–0.02000.04000.0250––131,072llama3apiopenrouter
Meta-Llama-3.1-8B-Instruct-Turbo 2 sourcesDeepInfra––0.02000.04000.0250––131,072–officialofficial-deepinfra
Llama 3.1 8B Instruct 2 sourcesNovita AI––0.02000.05000.0275––131,072llama3aggregatorlitellm
Llama 3.1 8B InstructLambda discontinued––0.02500.04000.0288––128,000–aggregatorlitellm
Mistral NemoOpenRouter––0.02900.03000.0293––131,072mistralapiopenrouter
Mistral NemoDeepInfrafp8–0.02900.03000.0293––131,072mistralapiopenrouter
Mistral-Nemo-Instruct-2407 2 sourcesDeepInfra––0.02900.03000.0293––131,072–officialofficial-deepinfra
Mistral NemoParasailfp8–0.03000.03000.0300––131,072mistralapiopenrouter
Llama Prompt Guard 2 22M 2 sourcesGroq––0.03000.03000.0300––512–aggregatorlitellm
llama-guard-3-8bNebius AI Studio––0.02000.06000.0300––131,072–aggregatorlitellm
meta-llama/Meta-Llama-3.1-8B-InstructNebius AI Studio––0.02000.06000.0300––131,072–aggregatorlitellm
Qwen/Qwen2-VL-7B-InstructNebius AI Studio––0.02000.06000.0300––32,768–aggregatorlitellm
DeepSeek-OCR 2 sourcesNovita AI––0.03000.03000.0300––8,192–aggregatorlitellm
Qwen3 4B 2 sourcesNovita AI––0.03000.03000.0300––128,000–aggregatorlitellm
DeepSeek OCR 2 2 sourcesNovita AI––0.03000.03000.0300––8,192–aggregatorlitellm
wan-2-6-imageTogether AI–––0.03000.0300––––officialofficial-together
flux-2-proTogether AI–––0.03000.0300––––officialofficial-together
flux-2-flexTogether AI–––0.03000.0300––––officialofficial-together
bytedance-seedream-4-0Together AI–––0.03000.0300––––officialofficial-together
GLM-OCRZhipu AI (Z.ai)––0.03000.03000.0300––––officialofficial-zhipu
ExtractOpenRouter––0.0400free0.0300––1,000,000–apiopenrouter
SummarizeOpenRouter––0.0400free0.0300––1,000,000–apiopenrouter
Ling 3.0 Flash VLOpenRouter––0.02100.06160.03120.004200–131,072–apiopenrouter
Ling 3.0 FlashOpenRouter––0.02100.06300.03150.004200–262,144–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