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 writeContextTokenizerLast changeConfidence?Source
tev1-4b-experimental 2 sourcesTogether AI––0.0420free0.0315––32,768–2026-11-11 ↑officialofficial-together
gpt-image-1.5Together AI–––0.03400.0340–––––officialofficial-together
meta-llama/Meta-Llama-3.1-8B-InstructDeepInfra––0.03000.05000.0350––131,072––aggregatorlitellm
Llama 3.2 3B Instruct 2 sourcesNovita AI––0.03000.05000.0350––131,072llama32026-01-13 ↓aggregatorlitellm
qwen-image-20Together AI–––0.03500.0350––––2026-11-11 ↓officialofficial-together
seedream-50-liteTogether AI–––0.03500.0350–––––officialofficial-together
gpt-oss-20bDarkbloomfp8–0.01800.09000.03600.009000–131,072o200k–apiopenrouter
gpt-oss-20bAkashMLfp4–0.01800.09000.03600.009000–131,072o200k2026-11-16 ↓apiopenrouter
meta-llama/Meta-Llama-3-8B-InstructDeepInfra––0.03000.06000.0375––8,192–2025-08-22 ↓aggregatorlitellm
Qwen3 Reranker 8BNovita AI––0.0500free0.0375––32,768––aggregatormodelsdev
Extractscaledown promo −20%––0.0500free0.0375––1,000,000––apiopenrouter
Summarizescaledown promo −20%––0.0500free0.0375––1,000,000––apiopenrouter
gemini-flash-image-2-5Together AI–––0.03900.0390–––––officialofficial-together
Ministral 3B 2 sourcesAzure AI Foundry––0.04000.04000.0400––128,000––aggregatorlitellm
Prompt Guard 2 86M 2 sourcesGroq––0.04000.04000.0400––512––aggregatorlitellm
Voxtral Mini 3B 2507 2 sourcesAWS Bedrock––0.04000.04000.0400––32,768––aggregatorlitellm
Llama 3 8B Instruct 2 sourcesNovita AI––0.04000.04000.0400––8,192–2026-01-13 ↓aggregatorlitellm
Gemma 4 E4B IT 2 sourcesDeepInfra––0.02000.1000.0400––131,072––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––0.01700.1120.0408––131,000––apiopenrouter
Llama 3 8B LunarisOpenRouter––0.04000.05000.0425––8,192llama3–apiopenrouter
Llama 3 8B LunarisParasail––0.04000.05000.0425––8,192llama3–apiopenrouter
Llama 3 8B LunarisDeepInfrafp8+turbo–0.04000.05000.0425––8,192llama3–apiopenrouter
Sao10K/L3-8B-Lunaris-v1-TurboDeepInfra––0.04000.05000.0425––8,192–2025-10-04 ↑aggregatorlitellm
Gemma 3 4BParasail––0.04000.05000.04250.0200–131,072gemini–apiopenrouter
Nex-N2.5-MiniOpenRouter––0.02500.1000.04380.002500–262,144qwen2–apiopenrouter
Nex-N2.5-MiniNex AGI––0.02500.1000.04380.002500–262,144qwen2–apiopenrouter
gpt-oss-120bPrime Intellectfp4–0.03500.07500.04500.0310–131,072o200k2026-11-09 ↕apiopenrouter
gpt-oss-20bDeepInfraflex–0.02400.1120.04600.0120–131,072o200k–apiopenrouter
gemini-31-flash-imageTogether AI–––0.04660.0466––––2026-11-11 ↓officialofficial-together
Llama 3.2 11b Vision InstructDeepInfra––0.04900.04900.0490––131,072––aggregatorlitellm
Gemma 3 4B 2 sourcesAWS Bedrock––0.04000.08000.0500––131,072gemini–aggregatorlitellm
Sao10k L3 8B Lunaris 2 sourcesNovita AI––0.05000.05000.0500––8,192–2026-01-13 ↓aggregatorlitellm
L3 8B Stheno V3.2 2 sourcesNovita AI––0.05000.05000.0500––8,192–2026-01-13 ↓aggregatorlitellm
Gemma 4 E2B IT 2 sourcesAWS Bedrock––0.04000.08000.0500––128,000––aggregatorlitellm
Rerank 5 ProCohere––0.0500–0.0500–––––officialofficial-cohere
Gemma 3 4BDeepInfraflex–0.04000.08000.0500––131,072gemini–apiopenrouter
Gemma 4 26B A4BPrime Intellect––0.03400.1010.05080.0170–262,144gemma2026-11-14 ↑apiopenrouter
Nemotron 3.5 Lightning 30B A3BPerplexity––0.01150.1700.05110.001150–262,144––aggregatorlitellm
Gemma 3 4BAWS Bedrock–ap-southeast-20.04120.08240.0515––131,072gemini–aggregatorlitellm
LFM2-24B-A2BTogether AI––0.03000.1200.0525––32,768––aggregatormodelsdev
Qwen3-Embedding-8BNovita AI––0.0700free0.0525––40,960––aggregatormodelsdev
gpt-image-2Together AI–––0.05300.0530–––––officialofficial-together
Qwen3.7 FlashOpenRouter––0.03000.1300.05500.0060000.03801,000,000qwen2–apiopenrouter
Qwen3.7 Flash 2 sourcesAlibaba Cloud––0.03000.1300.05500.0060000.03801,000,000qwen2–apiopenrouter
gpt-oss-20bCoreWeavefp4–0.03000.1300.05500.0300–131,072o200k–apiopenrouter
Qwen2.5 7B InstructDeepInfra––0.04000.1000.0550––32,768––aggregatorlitellm
llama-guard-3-8bDeepInfra––0.05500.05500.0550––131,072––aggregatorlitellm
gpt-oss-20bDekaLLM––0.02900.1400.05680.0290–131,072o200k–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