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 outContextTokenizerConfidence?
GPT-5 nanoOpenRouter––0.05000.4000.138––400,000o200kapi
Qwen3.5-9BParasail––0.1000.2500.138––262,144qwen2api
GPT-5 nano 3 sourcesAzure AI Foundry––0.05000.4000.1380.02500.200400,000o200kapi
GPT-5 nano 3 sourcesOpenAI––0.05000.4000.1380.02500.200400,000o200kapi
Gemma 4 26B A4B 3 sourcesDeepInfra––0.07000.3400.138––262,144gemmaofficial
Gemma 4 26B A4BMakora––0.09000.2800.138––262,144gemmaapi
GPT-5 nanoPerplexity––0.05000.4000.138––400,000o200kaggregator
Gemma 3 27B 3 sourcesNovita AI––0.1190.2000.139––131,072geminiapi
Phi 4 MultimodalAzure AI Foundry––0.08000.3200.140––131,072–aggregator
Gemma 3 12B 2 sourcesAWS Bedrock––0.09000.2900.1400.05000.150131,072geminiaggregator
Hermes 2 Pro Llama 3 8B 2 sourcesNovita AI––0.1400.1400.140––8,192–aggregator
Phi-4-multimodalAzure AI Foundry––0.08000.3200.140––128,000–aggregator
Gemma 4 26B A4BNextBit promo −15%––0.09000.3000.143––262,144gemmaapi
Qwen3 30B A3B Instruct 2507DekaLLM––0.09000.3000.143––262,144qwen2api
Qwen3 30B A3B Instruct 2507SiliconFlowfp8–0.09000.3000.143––262,144qwen2api
Mistral Small 3.2 24BParasail––0.09000.3000.143––256,000mistralapi
Llama Guard 4 12BDeepInfraflex–0.1440.1440.144––163,840–api
Gemma 3 12BAWS Bedrock–ap-southeast-20.09270.2990.144––131,072geminiaggregator
Hy3Tencent Cloudfp8+off-peak–0.08250.3300.144––262,144–api
Hy3OpenRouteroff-peak–0.08250.3300.144––262,144–api
MiMo-V2.6-Flashio.netfp8–0.1000.2800.145––1,050,000–api
MiMo-V2.6-FlashDarkbloomfp4–0.1000.2800.145––1,050,000–api
GLM 4.7 Flash 2 sourcesDeepInfra––0.06000.4000.145––200,000–aggregator
gpt-oss-120bSAIL Researchfp4–0.06000.4000.145––131,072o200kapi
GLM 4.7 FlashOpenRouter––0.06050.4000.145––200,000–api
GLM 4.7 FlashCloudflare Workers AI––0.06050.4000.145––200,000–api
DeepSeek V4.1 Flash 1017ambientfp4–0.09800.2940.147––1,048,576deepseekapi
Gemma 3 27BNextBitfp8–0.08000.3500.148––131,072geminiapi
gpt-oss-20bAWS Bedrock–ap-south-10.08000.3500.148––131,072o200kaggregator
MiMo-V2.5OpenRouter––0.1190.2380.149––1,000,000–api
DeepSeek V4 Flash 0731DigitalOcean––0.1190.2380.149––1,048,576deepseekapi
Ministral 3 8B 2512OpenRouter––0.1500.1500.150––262,144mistralapi
Voxtral Small 24B 2507OpenRouter––0.1000.3000.150––32,768mistralapi
Qwen3 30B A3B Instruct 2507OpenRouter––0.1000.3000.150––262,144qwen2api
Qwen3 14BOpenRouter––0.1200.2400.150––40,960qwen2api
Llama 4 ScoutOpenRouter––0.1000.3000.150––10,000,000llama3api
DeepSeek V4 FlashRelacefp4–0.05000.4500.150––1,048,576deepseekapi
Step 3.5 FlashSiliconFlowfp8–0.1000.3000.150––262,144–api
Ministral 3 8B 2512Mistral AIzdr–0.1500.1500.150––262,144mistralapi
Ministral 3 8B 2512 3 sourcesMistral AI––0.1500.1500.150––262,144mistralapi
Voxtral Small 24B 2507Mistral AIzdr–0.1000.3000.150––32,768mistralapi
Voxtral Small 24B 2507Mistral AI––0.1000.3000.150––32,768mistralapi
gpt-oss-120bDigitalOcean––0.06000.4200.150––131,072o200kapi
Qwen3 30B A3B Instruct 2507Nebius AI Studiofp8–0.1000.3000.150––262,144qwen2api
Mistral Small 3.2 24BMistral AI–eu0.1000.3000.150––256,000mistralapi
Qwen3 14BDeepInfrafp8–0.1200.2400.150––40,960qwen2api
Llama 4 ScoutDeepInfrafp8–0.1000.3000.150––10,000,000llama3api
Gemma 3 27BNebius AI Studiofp8–0.1000.3000.150––131,072geminiapi
Mistral NemoMistral AI–eu0.1500.1500.150––131,072mistralapi
Mistral NemoAzure AI Foundry––0.1500.1500.150––131,072mistralaggregator

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