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 ↑?Batch inBatch outContextConfidence?
tev1-4b-experimental 2 sourcesTogether AI––0.0420free0.0315––32,768official
gpt-image-1.5Together AI–––0.03400.0340–––official
meta-llama/Meta-Llama-3.1-8B-InstructDeepInfra––0.03000.05000.0350––131,072aggregator
Llama 3.2 3B Instruct 2 sourcesNovita AI––0.03000.05000.0350––131,072aggregator
qwen-image-20Together AI–––0.03500.0350–––official
seedream-50-liteTogether AI–––0.03500.0350–––official
gpt-oss-20bDarkbloomfp8–0.01800.09000.0360––131,072api
gpt-oss-20bAkashMLfp4–0.01800.09000.0360––131,072api
meta-llama/Meta-Llama-3-8B-InstructDeepInfra––0.03000.06000.0375––8,192aggregator
Qwen3 Reranker 8BNovita AI––0.0500free0.0375––32,768aggregator
Extractscaledown promo −20%––0.0500free0.0375––1,000,000api
Summarizescaledown promo −20%––0.0500free0.0375––1,000,000api
gemini-flash-image-2-5Together AI–––0.03900.0390–––official
Ministral 3B 2 sourcesAzure AI Foundry––0.04000.04000.0400––128,000aggregator
Prompt Guard 2 86M 2 sourcesGroq––0.04000.04000.0400––512aggregator
Voxtral Mini 3B 2507 2 sourcesAWS Bedrock––0.04000.04000.04000.02000.020032,768aggregator
Llama 3 8B Instruct 2 sourcesNovita AI––0.04000.04000.0400––8,192aggregator
Gemma 4 E4B IT 2 sourcesDeepInfra––0.02000.1000.0400––131,072aggregator
flux-1-kontext-proTogether AI––0.0400–0.0400–––official
flux1-1-proTogether AI––0.0400–0.0400–––official
Granite 4.0 MicroCloudflare Workers AI––0.01700.1120.0408––131,000api
Llama 3 8B LunarisOpenRouter––0.04000.05000.0425––8,192api
Llama 3 8B LunarisParasail––0.04000.05000.0425––8,192api
Llama 3 8B LunarisDeepInfrafp8+turbo–0.04000.05000.0425––8,192api
Sao10K/L3-8B-Lunaris-v1-TurboDeepInfra––0.04000.05000.0425––8,192aggregator
Gemma 3 4BParasail––0.04000.05000.0425––131,072api
Nex-N2.5-MiniOpenRouter––0.02500.1000.0438––262,144api
Nex-N2.5-MiniNex AGI––0.02500.1000.0438––262,144api
gpt-oss-120bPrime Intellectfp4–0.03500.07500.0450––131,072api
gpt-oss-20bDeepInfraflex–0.02400.1120.0460––131,072api
gemini-31-flash-imageTogether AI–––0.04660.0466–––official
Llama 3.2 11b Vision InstructDeepInfra––0.04900.04900.0490––131,072aggregator
Gemma 3 4B 2 sourcesAWS Bedrock––0.04000.08000.05000.02000.0400131,072aggregator
Sao10k L3 8B Lunaris 2 sourcesNovita AI––0.05000.05000.0500––8,192aggregator
L3 8B Stheno V3.2 2 sourcesNovita AI––0.05000.05000.0500––8,192aggregator
Gemma 4 E2B IT 2 sourcesAWS Bedrock––0.04000.08000.05000.02000.0400128,000aggregator
Rerank 5 ProCohere––0.0500–0.0500–––official
Gemma 3 4BDeepInfraflex–0.04000.08000.0500––131,072api
Gemma 4 26B A4BPrime Intellect––0.03400.1010.0508––262,144api
Nemotron 3.5 Lightning 30B A3BPerplexity––0.01150.1700.0511––262,144aggregator
Gemma 3 4BAWS Bedrock–ap-southeast-20.04120.08240.0515––131,072aggregator
LFM2-24B-A2BTogether AI––0.03000.1200.0525––32,768aggregator
Qwen3-Embedding-8BNovita AI––0.0700free0.0525––40,960aggregator
gpt-image-2Together AI–––0.05300.0530–––official
Qwen3.7 FlashOpenRouter––0.03000.1300.0550––1,000,000api
Qwen3.7 Flash 2 sourcesAlibaba Cloud––0.03000.1300.0550––1,000,000api
gpt-oss-20bCoreWeavefp4–0.03000.1300.0550––131,072api
Qwen2.5 7B InstructDeepInfra––0.04000.1000.0550––32,768aggregator
llama-guard-3-8bDeepInfra––0.05500.05500.0550––131,072aggregator
gpt-oss-20bDekaLLM––0.02900.1400.0568––131,072api

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