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 ↑?Batch inBatch outContextTokenizerLast changeConfidence?
tev1-4b-experimental 2 sourcesTogether AITogether AI––0.0420free0.0315––32,768–2026-11-11 ↑official
gpt-image-1.5OpenAITogether AI–––0.03400.0340–––––official
meta-llama/Meta-Llama-3.1-8B-InstructMetaDeepInfra––0.03000.05000.0350––131,072––aggregator
Llama 3.2 3B Instruct 2 sourcesMetaNovita AI––0.03000.05000.0350––131,072llama32026-01-13 ↓aggregator
qwen-image-20Together AITogether AI–––0.03500.0350––––2026-11-11 ↓official
seedream-50-liteTogether AITogether AI–––0.03500.0350–––––official
gpt-oss-20bOpenAIDarkbloomfp8–0.01800.09000.0360––131,072o200k–api
gpt-oss-20bOpenAIAkashMLfp4–0.01800.09000.0360––131,072o200k2026-11-16 ↓api
meta-llama/Meta-Llama-3-8B-InstructMetaDeepInfra––0.03000.06000.0375––8,192–2025-08-22 ↓aggregator
Qwen3 Reranker 8BAlibaba CloudNovita AI––0.0500free0.0375––32,768––aggregator
Extractscaledownscaledown promo −20%––0.0500free0.0375––1,000,000––api
Summarizescaledownscaledown promo −20%––0.0500free0.0375––1,000,000––api
gemini-flash-image-2-5Together AITogether AI–––0.03900.0390–––––official
Ministral 3B 2 sourcesAzure AI FoundryAzure AI Foundry––0.04000.04000.0400––128,000––aggregator
Prompt Guard 2 86M 2 sourcesMetaGroq––0.04000.04000.0400––512––aggregator
Voxtral Mini 3B 2507 2 sourcesMistral AIAWS Bedrock––0.04000.04000.04000.02000.020032,768––aggregator
Llama 3 8B Instruct 2 sourcesMetaNovita AI––0.04000.04000.0400––8,192–2026-01-13 ↓aggregator
Gemma 4 E4B IT 2 sourcesGoogleDeepInfra––0.02000.1000.0400––131,072––aggregator
flux-1-kontext-proTogether AITogether AI––0.0400–0.0400–––––official
flux1-1-proTogether AITogether AI––0.0400–0.0400–––––official
Granite 4.0 MicroOpenRouterCloudflare Workers AI––0.01700.1120.0408––131,000––api
Llama 3 8B LunarisOpenRouterOpenRouter––0.04000.05000.0425––8,192llama3–api
Llama 3 8B LunarisOpenRouterParasail––0.04000.05000.0425––8,192llama3–api
Llama 3 8B LunarisOpenRouterDeepInfrafp8+turbo–0.04000.05000.0425––8,192llama3–api
Sao10K/L3-8B-Lunaris-v1-TurboDeepInfraDeepInfra––0.04000.05000.0425––8,192–2025-10-04 ↑aggregator
Gemma 3 4BGoogleParasail––0.04000.05000.0425––131,072gemini–api
Nex-N2.5-MiniOpenRouterOpenRouter––0.02500.1000.0438––262,144qwen2–api
Nex-N2.5-MiniOpenRouterNex AGI––0.02500.1000.0438––262,144qwen2–api
gpt-oss-120bOpenAIPrime Intellectfp4–0.03500.07500.0450––131,072o200k2026-11-09 ↕api
gpt-oss-20bOpenAIDeepInfraflex–0.02400.1120.0460––131,072o200k–api
gemini-31-flash-imageTogether AITogether AI–––0.04660.0466––––2026-11-11 ↓official
Llama 3.2 11b Vision InstructMetaDeepInfra––0.04900.04900.0490––131,072––aggregator
Gemma 3 4B 2 sourcesGoogleAWS Bedrock––0.04000.08000.05000.02000.0400131,072gemini–aggregator
Sao10k L3 8B Lunaris 2 sourcesNovita AINovita AI––0.05000.05000.0500––8,192–2026-01-13 ↓aggregator
L3 8B Stheno V3.2 2 sourcesNovita AINovita AI––0.05000.05000.0500––8,192–2026-01-13 ↓aggregator
Gemma 4 E2B IT 2 sourcesGoogleAWS Bedrock––0.04000.08000.05000.02000.0400128,000––aggregator
Rerank 5 ProCohereCohere––0.0500–0.0500–––––official
Gemma 3 4BGoogleDeepInfraflex–0.04000.08000.0500––131,072gemini–api
Gemma 4 26B A4BGooglePrime Intellect––0.03400.1010.0508––262,144gemma2026-11-14 ↑api
Nemotron 3.5 Lightning 30B A3BNVIDIAPerplexity––0.01150.1700.0511––262,144––aggregator
Gemma 3 4BGoogleAWS Bedrock–ap-southeast-20.04120.08240.0515––131,072gemini–aggregator
LFM2-24B-A2BTogether AITogether AI––0.03000.1200.0525––32,768––aggregator
Qwen3-Embedding-8BAlibaba CloudNovita AI––0.0700free0.0525––40,960––aggregator
gpt-image-2OpenAITogether AI–––0.05300.0530–––––official
Qwen3.7 FlashAlibaba CloudOpenRouter––0.03000.1300.0550––1,000,000qwen2–api
Qwen3.7 Flash 2 sourcesAlibaba CloudAlibaba Cloud––0.03000.1300.0550––1,000,000qwen2–api
gpt-oss-20bOpenAICoreWeavefp4–0.03000.1300.0550––131,072o200k–api
Qwen2.5 7B InstructAlibaba CloudDeepInfra––0.04000.1000.0550––32,768––aggregator
llama-guard-3-8bMetaDeepInfra––0.05500.05500.0550––131,072––aggregator
gpt-oss-20bOpenAIDekaLLM––0.02900.1400.0568––131,072o200k–api

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