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 outContextLast changeConfidence?Source
GPT-5 nanoOpenAIOpenRouter––0.05000.4000.1380.005000–––400,000–apiopenrouter
Qwen3.5-9BAlibaba CloudParasail––0.1000.2500.138––––262,144–apiopenrouter
GPT-5 nano 3 sourcesOpenAIAzure AI Foundry––0.05000.4000.1380.0100–0.02500.200400,000–apiopenrouter
GPT-5 nano 3 sourcesOpenAIOpenAI––0.05000.4000.1380.005000–0.02500.200400,000–apiopenrouter
Gemma 4 26B A4B 3 sourcesGoogleDeepInfra––0.07000.3400.138––––262,144–officialofficial-deepinfra
Gemma 4 26B A4BGoogleMakora––0.09000.2800.1380.0490–––262,1442026-11-13 ↑apiopenrouter
GPT-5 nanoOpenAIPerplexity––0.05000.4000.1380.005000–––400,000–aggregatorlitellm
Gemma 3 27B 3 sourcesGoogleNovita AI––0.1190.2000.139––––131,0722026-01-13 ↓apiopenrouter
Phi 4 MultimodalMicrosoftAzure AI Foundry––0.08000.3200.140––––131,0722025-04-14 ↓aggregatorlitellm
Gemma 3 12B 2 sourcesGoogleAWS Bedrock––0.09000.2900.140––0.05000.150131,072–aggregatorlitellm
Hermes 2 Pro Llama 3 8B 2 sourcesNovita AINovita AI––0.1400.1400.140––––8,1922026-01-13 ↓aggregatorlitellm
Phi-4-multimodalMicrosoftAzure AI Foundry––0.08000.3200.140––––128,000–aggregatormodelsdev
Gemma 4 26B A4BGoogleNextBit promo −15%––0.09000.3000.1430.0500–––262,144–apiopenrouter
Qwen3 30B A3B Instruct 2507Alibaba CloudDekaLLM––0.09000.3000.143––––262,144–apiopenrouter
Qwen3 30B A3B Instruct 2507Alibaba CloudSiliconFlowfp8–0.09000.3000.143––––262,144–apiopenrouter
Mistral Small 3.2 24BMistral AIParasail––0.09000.3000.1430.0500–––256,000–apiopenrouter
Llama Guard 4 12BMetaDeepInfraflex–0.1440.1440.144––––163,840–apiopenrouter
Gemma 3 12BGoogleAWS Bedrock–ap-southeast-20.09270.2990.144––––131,072–aggregatorlitellm
Hy3OpenRouterTencent Cloudfp8+off-peak–0.08250.3300.1440.0206–––262,144–apiopenrouter
Hy3OpenRouterOpenRouteroff-peak–0.08250.3300.1440.0206–––262,144–apiopenrouter
MiMo-V2.6-FlashOpenRouterio.netfp8–0.1000.2800.1450.003000–––1,050,0002026-10-23 ↓apiopenrouter
MiMo-V2.6-FlashOpenRouterDarkbloomfp4–0.1000.2800.1450.0500–––1,050,0002026-10-06 ↓apiopenrouter
GLM 4.7 Flash 2 sourcesZhipu AI (Z.ai)DeepInfra––0.06000.4000.1450.0100–––200,000–aggregatorlitellm
gpt-oss-120bOpenAISAIL Researchfp4–0.06000.4000.1450.0300–––131,072–apiopenrouter
GLM 4.7 FlashZhipu AI (Z.ai)OpenRouter––0.06050.4000.145––––200,000–apiopenrouter
GLM 4.7 FlashZhipu AI (Z.ai)Cloudflare Workers AI––0.06050.4000.145––––200,000–apiopenrouter
DeepSeek V4.1 Flash 1017DeepSeekambientfp4–0.09800.2940.1470.002900–––1,048,576–apiopenrouter
Gemma 3 27BGoogleNextBitfp8–0.08000.3500.1480.0400–––131,072–apiopenrouter
gpt-oss-20bOpenAIAWS Bedrock–ap-south-10.08000.3500.148––––131,072–aggregatorlitellm
MiMo-V2.5OpenRouterOpenRouter––0.1190.2380.1490.002550–––1,000,000–apiopenrouter
DeepSeek V4 Flash 0731DeepSeekDigitalOcean––0.1190.2380.1490.0238–––1,048,576–apiopenrouter
Ministral 3 8B 2512Mistral AIOpenRouter––0.1500.1500.1500.0150–––262,144–apiopenrouter
Voxtral Small 24B 2507Mistral AIOpenRouter––0.1000.3000.1500.0100–––32,768–apiopenrouter
Qwen3 30B A3B Instruct 2507Alibaba CloudOpenRouter––0.1000.3000.1500.100–––262,144–apiopenrouter
Qwen3 14BAlibaba CloudOpenRouter––0.1200.2400.150––––40,960–apiopenrouter
Llama 4 ScoutMetaOpenRouter––0.1000.3000.150––––10,000,000–apiopenrouter
DeepSeek V4 FlashDeepSeekRelacefp4–0.05000.4500.1500.0500–––1,048,5762026-11-11 ↑apiopenrouter
Step 3.5 FlashOpenRouterSiliconFlowfp8–0.1000.3000.150––––262,144–apiopenrouter
Ministral 3 8B 2512Mistral AIMistral AIzdr–0.1500.1500.1500.0150–––262,144–apiopenrouter
Ministral 3 8B 2512 3 sourcesMistral AIMistral AI––0.1500.1500.1500.0150–––262,144–apiopenrouter
Voxtral Small 24B 2507Mistral AIMistral AIzdr–0.1000.3000.1500.0100–––32,768–apiopenrouter
Voxtral Small 24B 2507Mistral AIMistral AI––0.1000.3000.1500.0100–––32,768–apiopenrouter
gpt-oss-120bOpenAIDigitalOcean––0.06000.4200.1500.0120–––131,072–apiopenrouter
Qwen3 30B A3B Instruct 2507Alibaba CloudNebius AI Studiofp8–0.1000.3000.1500.100–––262,144–apiopenrouter
Mistral Small 3.2 24BMistral AIMistral AI–eu0.1000.3000.1500.0100–––256,000–apiopenrouter
Qwen3 14BAlibaba CloudDeepInfrafp8–0.1200.2400.150––––40,960–apiopenrouter
Llama 4 ScoutMetaDeepInfrafp8–0.1000.3000.150––––10,000,000–apiopenrouter
Gemma 3 27BGoogleNebius AI Studiofp8–0.1000.3000.1500.0400–––131,072–apiopenrouter
Mistral NemoMistral AIMistral AI–eu0.1500.1500.1500.0150–––131,072–apiopenrouter
Mistral NemoMistral AIAzure AI Foundry––0.1500.1500.150––––131,072–aggregatorlitellm

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