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 ↑?Cache readCache writeBatch inBatch outContextTokenizerLast changeConfidence?
accounts/fireworks/models/flux-1-dev-controlnet-unionFireworks AIFireworks AI––0.0010000.0010000.001000––––4,096––aggregator
juggernaut-lightning-fluxTogether AITogether AI–––0.0017000.001700–––––––official
sd-xlTogether AITogether AI–––0.0019000.001900–––––––official
p-image-ideogramTogether AITogether AI–––0.0022500.002250–––––––official
juggernaut-pro-fluxTogether AITogether AI–––0.0049000.004900–––––––official
Qwen ImageAlibaba CloudTogether AI–––0.0058000.005800–––––––official
Qwen3-Embedding-8BAlibaba CloudNebius AI Studio––0.0100free0.007500––––40,960––aggregator
BGE M3NVIDIANovita AI––0.0100free0.007500––––8,192––aggregator
BGE Reranker V2 M3Novita AINovita AI––0.0100free0.007500––––8,000––aggregator
Qwen/Qwen2.5-Coder-7BAlibaba CloudNebius AI Studio––0.01000.03000.0150––––32,768––aggregator
text-embedding-3-smallOpenAIAzure AI Foundry––0.0200free0.0150––––8,191––aggregator
text-embedding-3-smallOpenAIOpenAI––0.0200free0.0150––––8,191––aggregator
flux-2-devTogether AITogether AI–––0.01540.0154–––––––official
eu.meta.llama3-2-3b-instruct-v1:0MetaLambda discontinued––0.01500.02500.0175––––128,000––aggregator
bytedance-seedream-3-0Together AITogether AI–––0.01800.0180–––––––official
Llama 3.2 3B InstructMetaDeepInfra––0.02000.02000.0200––––131,072llama32025-10-04 ↕aggregator
PaddleOCR VL 2 sourcesNovita AINovita AI––0.02000.02000.0200––––16,384–2026-01-13 ↓aggregator
Llama 3.2 1B Instruct 2 sourcesMetaNovita AI––0.02000.02000.0200––––60,000llama3–aggregator
Qwen/Qwen2-1.5B-InstructAlibaba CloudTogether AI––0.02000.02000.0200––––32,768––aggregator
Rerank 5 FastCohereCohere––0.0200–0.0200–––––––official
Mistral NemoMistral AIDekaLLMfp8–0.01800.03000.0210––––131,072mistral–api
gpt-oss-20bOpenAIPrime Intellectfp4–0.02000.03000.02250.0180–––131,072o200k–api
Ling 3.0 Tinyant-digitalant-digitalfp8–0.01500.04500.02250.003000–––262,144––api
Ling 3.0 Tinyant-digitalOpenRouter––0.01500.04500.02250.003000–––262,144––api
Mistral NemoMistral AIio.net promo −28%––0.02300.03000.02480.0150–––131,072mistral2026-10-06 ↓api
Llama 3.1 8B InstructMetaOpenRouter––0.02000.04000.0250––––131,072llama3–api
Llama 3.1 8B InstructMetaDeepInfrafp8–0.02000.04000.0250––––131,072llama3–api
Meta-Llama-3.1-8B-Instruct-Turbo 2 sourcesMetaDeepInfra––0.02000.04000.0250––––131,072–2026-08-27 ↑official
Llama 3.1 8B Instruct 2 sourcesMetaNovita AI––0.02000.05000.0275––––131,072llama32026-01-13 ↓aggregator
Llama 3.1 8B InstructMetaLambda discontinued––0.02500.04000.0288––––128,000––aggregator
Mistral NemoMistral AIOpenRouter––0.02900.03000.0293––––131,072mistral–api
Mistral NemoMistral AIDeepInfrafp8–0.02900.03000.0293––––131,072mistral2026-10-09 ↑api
Mistral-Nemo-Instruct-2407 2 sourcesMistral AIDeepInfra––0.02900.03000.0293––––131,072–2026-10-09 ↑official
Mistral NemoMistral AIParasailfp8–0.03000.03000.0300––––131,072mistral–api
Llama Prompt Guard 2 22M 2 sourcesMetaGroq––0.03000.03000.0300––––512––aggregator
llama-guard-3-8bMetaNebius AI Studio––0.02000.06000.0300––––131,072––aggregator
meta-llama/Meta-Llama-3.1-8B-InstructMetaNebius AI Studio––0.02000.06000.0300––––131,072––aggregator
Qwen/Qwen2-VL-7B-InstructAlibaba CloudNebius AI Studio––0.02000.06000.0300––––32,768––aggregator
DeepSeek-OCR 2 sourcesDeepSeekNovita AI––0.03000.03000.0300––––8,192–2026-01-13 ↓aggregator
Qwen3 4B 2 sourcesAlibaba CloudNovita AI––0.03000.03000.0300––––128,000–2026-01-13 ↓aggregator
DeepSeek OCR 2 2 sourcesDeepSeekNovita AI––0.03000.03000.0300––––8,192––aggregator
wan-2-6-imageTogether AITogether AI–––0.03000.0300–––––––official
flux-2-proTogether AITogether AI–––0.03000.0300–––––––official
flux-2-flexTogether AITogether AI–––0.03000.0300–––––––official
bytedance-seedream-4-0Together AITogether AI–––0.03000.0300–––––––official
GLM-OCRZhipu AI (Z.ai)Zhipu AI (Z.ai)––0.03000.03000.0300–––––––official
ExtractscaledownOpenRouter––0.0400free0.0300––––1,000,000––api
SummarizescaledownOpenRouter––0.0400free0.0300––––1,000,000––api
Ling 3.0 Flash VLOpenRouterOpenRouter––0.02100.06160.03120.004200–––131,072––api
Ling 3.0 FlashOpenRouterOpenRouter––0.02100.06300.03150.004200–––262,144––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