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 tier-tagged and vendor-direct models. Show all offerings, including the long tail

More columns: + Vendor + Region - Cache + Batch + Tokenizer - Last change - Source All columns Default columns

ModelHostVariantRegionInputOutputBlended ↑?Cache readCache writeContextLast changeConfidence?Source
GPT-5 miniPerplexity––0.2502.000.6880.0250–400,000–aggregatorlitellm
Qwen3-Coder-480B-A35B 2 sourcesDeepInfra––0.4001.600.7000.100–262,1442026-08-27 ↕aggregatorlitellm
GLM-4.6DeepInfraflex+fp4–0.4001.600.7000.0800–200,000–apiopenrouter
Llama 3.3 70B InstructOpenRouter––0.7100.7100.7100.710–128,000–apiopenrouter
Llama 3.3 70B InstructCoreWeave––0.7100.7100.7100.710–128,000–apiopenrouter
Llama 3.3 70B Instruct 2 sourcesAzure AI Foundry––0.7100.7100.710––128,000–aggregatorlitellm
Llama 3.3 70B InstructGoogle Vertex AI–us-central10.7200.7200.720––128,000–apiopenrouter
Llama 3.3 70B Instruct 3 sourcesGoogle Vertex AI––0.7200.7200.720––128,000–apiopenrouter
Llama 3.3 70B Instruct 2 sourcesAWS Bedrock––0.7200.7200.720––128,000–aggregatorlitellm
Llama 3.3 70B InstructAWS Bedrock–us0.7200.7200.720––128,000–aggregatorlitellm
Mistral Large 3 (25.12)OpenRouter––0.5001.500.7500.0500–262,144–apiopenrouter
Mistral Large 3 (25.12)Mistral AIzdr–0.5001.500.7500.0500–262,144–apiopenrouter
Llama 3.3 70B Instruct 2 sourcesSambaNova––0.6001.200.750––128,000–apiopenrouter
Mistral Large 3 (25.12)Azure AI Foundry––0.5001.500.750––262,144–aggregatorlitellm
Mistral Large 3 (25.12) 2 sourcesAWS Bedrock––0.5001.500.750––262,144–aggregatorlitellm
Mistral Large 3 (25.12) 2 sourcesMistral AI––0.5001.500.7500.0500–262,1442026-03-02 ↓aggregatorlitellm
GPT-5 miniAzure AI Foundry–swedencentral0.2752.200.7560.0330–400,000–apiopenrouter
GPT-5 miniAzure AI Foundry–eu0.2752.200.7560.0275–400,000–aggregatorlitellm
GPT-5 miniAzure AI Foundry–us0.2752.200.7560.0275–400,000–aggregatorlitellm
GLM-4.6Venicefp4–0.4301.750.7600.0800–200,000–apiopenrouter
Mistral Large 3 (25.12)AWS Bedrock–ap-southeast-20.5151.550.773––262,144–aggregatorlitellm
Llama 3.3 70B InstructCloudflare Workers AIfp8–0.2932.250.783––128,000–apiopenrouter
Qwen3-Coder-480B-A35B 2 sourcesAWS Bedrock––0.4501.800.788––262,1442026-09-06 ↑aggregatorlitellm
Qwen3-Coder-480B-A35BFireworks AI––0.4501.800.788––262,144–aggregatorlitellm
Qwen3-235B-A22B 2 sourcesAlibaba Cloud––0.4551.820.796––131,072–apiopenrouter
Mistral Medium 3.1Mistral AI––0.4002.000.800––131,072–aggregatormodelsdev
Qwen3-Coder-480B-A35BAWS Bedrock–ap-southeast-20.4641.850.811––262,144–aggregatorlitellm
Qwen3-Coder-480B-A35BAWS Bedrock–ap-southeast-30.4701.870.820––262,144–aggregatorlitellm
Mistral Large 3 (25.12)Mistral AI–eu0.5501.650.8250.0550–262,144–apiopenrouter
Gemini 2.5 FlashOpenRouter––0.3002.500.8500.03000.08331,048,576–apiopenrouter
MiniMax-M1MiniMax––0.4002.200.850––1,000,000–apiopenrouter
Gemini 2.5 Flash 4 sourcesGoogle––0.3002.500.8500.03000.08331,048,576–officialofficial-google
Gemini 2.5 Flash 3 sourcesGoogle Vertex AI––0.3002.500.8500.03000.08331,048,576–apiopenrouter
Gemini 2.5 Flash 2 sourcesDeepInfra––0.3002.500.850––1,048,5762025-10-04 ↑officialofficial-deepinfra
GLM-4.6OpenRouter––0.5002.000.8750.100–200,000–apiopenrouter
GLM-4.6DeepInfrafp4–0.5002.000.8750.100–200,000–apiopenrouter
Kimi K2DeepInfra––0.5002.000.875––131,072–aggregatorlitellm
GLM-4.6 3 sourcesDeepInfra––0.5002.000.8750.100–200,000–officialofficial-deepinfra
DeepSeek V3.2 (chat)Together AI––0.6001.700.875––128,000–aggregatorlitellm
Mistral Large 3 (25.12)AWS Bedrock–ap-south-10.5901.760.883––262,144–aggregatorlitellm
Mistral Large 3 (25.12)AWS Bedrock–ap-northeast-10.6101.820.913––262,144–aggregatorlitellm
Mistral Large 3 (25.12)AWS Bedrock–sa-east-10.6101.820.913––262,144–aggregatorlitellm
Llama 4 MaverickSambaNova––0.6301.800.923––1,000,000–aggregatorlitellm
Qwen3-Coder-480B-A35BAWS Bedrock–ap-south-10.5302.120.928––262,144–aggregatorlitellm
Qwen3-Coder-480B-A35BAWS Bedrock–sa-east-10.5402.160.945––262,144–aggregatorlitellm
Qwen3-Coder-480B-A35BAWS Bedrock–ap-northeast-10.5402.180.950––262,144–aggregatorlitellm
GLM-4.6 3 sourcesNovita AI––0.5502.200.9630.110–200,0002026-01-13 ↓apiopenrouter
MiniMax-M1 3 sourcesNovita AI––0.5502.200.963––1,000,0002026-01-13 ↓apiopenrouter
DeepSeek V4 ProDeepSeekoff-peak–0.6601.980.9900.0220–1,048,576–officialofficial-deepseek
GLM-4.6Zhipu AI (Z.ai)fp4–0.6002.201.000.110–200,000–apiopenrouter

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