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 writeContextTokenizerLast changeConfidence?Source
DeepSeek V4 FlashParasailfp8–0.1400.2800.1750.0700–1,048,576deepseek–apiopenrouter
Gemini 2.5 Flash-Lite 3 sourcesGoogle Vertex AI––0.1000.4000.1750.01000.08331,048,576gemini–apiopenrouter
Gemini 2.5 Flash-Lite 4 sourcesGoogle––0.1000.4000.1750.01000.08331,048,576gemini–officialofficial-google
Llama 3.3 Nemotron Super 49B v1 2 sourcesDeepInfra––0.1000.4000.175––131,072llama3–aggregatorlitellm
Llama 3.3 Nemotron Super 49B v1Nebius AI Studio––0.1000.4000.175––131,072llama3–aggregatorlitellm
DeepSeek V4 FlashNebius AI Studio––0.1400.2800.175––1,048,576deepseek–aggregatorlitellm
DeepSeek V4 Flash 2 sourcesNovita AI––0.1400.2800.1750.0280–1,048,576deepseek–aggregatorlitellm
Llama 3.3 70B InstructNebius AI Studio––0.1300.4000.198––128,000llama3–aggregatorlitellm
GPT-6 LunaOpenRouter––0.1000.5000.2000.01000.1251,050,000o200k–apiopenrouter
GPT-6 Luna 4 sourcesOpenAI––0.1000.5000.2000.01000.1251,050,000o200k–officialofficial-openai
GPT-6 Luna 3 sourcesAzure AI Foundry––0.1000.5000.2000.01000.1251,050,000o200k–apiopenrouter
GPT-6 Luna 2 sourcesAWS Bedrock––0.1000.5000.2000.01000.1251,050,000o200k–aggregatorlitellm
GPT-6 LunaPerplexity––0.1000.5000.2000.0100–1,050,000o200k–aggregatorlitellm
GPT-6 Luna 2 sourcesAWS Bedrock–global0.1000.5000.2000.01000.1251,050,000o200k–apiopenrouter
Claude Haiku 5.5 3 sourcesAWS Bedrock––0.1000.5000.2000.01000.1251,000,000claude–apiopenrouter
Claude Haiku 5.5 4 sourcesAnthropic––0.1000.5000.2000.01000.1251,000,000claude–officialofficial-anthropic
Claude Haiku 5.5Azure AI Foundry–global0.1000.5000.2000.01000.1251,000,000claude–apiopenrouter
Claude Haiku 5.5Claude on AWS––0.1000.5000.2000.01000.1251,000,000claude–apiopenrouter
Claude Haiku 5.5Google Vertex AI–global0.1000.5000.2000.01000.1251,000,000claude–apiopenrouter
Claude Haiku 5.5OpenRouter––0.1000.5000.2000.01000.1251,000,000claude–apiopenrouter
Claude Haiku 5.5AWS Bedrock–global0.1000.5000.2000.01000.1251,000,000claude–aggregatorlitellm
Claude Haiku 5.5Perplexity––0.1000.5000.2000.0100–1,000,000claude–aggregatorlitellm
Claude Haiku 5.5 2 sourcesAzure AI Foundry––0.1000.5000.2000.01000.1251,000,000claude–aggregatorlitellm
Claude Haiku 5.5 2 sourcesGoogle Vertex AI––0.1000.5000.2000.01000.1251,000,000claude–aggregatorlitellm
Llama 3.3 70B Instruct 3 sourcesNovita AI––0.1350.4000.201––128,000llama32026-01-13 ↓apiopenrouter
Phi-4 2 sourcesAzure AI Foundry––0.1250.5000.219––16,384––aggregatorlitellm
GPT-6 Luna 2 sourcesAzure AI Foundry–us0.1100.5500.2200.01100.1381,050,000o200k–apiopenrouter
GPT-6 Luna 2 sourcesAzure AI Foundry–eu0.1100.5500.2200.01100.1381,050,000o200k–apiopenrouter
GPT-6 LunaAWS Bedrock–us-east-10.1100.5500.2200.01100.1381,050,000o200k–apiopenrouter
GPT-6 LunaAWS Bedrock–us0.1100.5500.2200.01100.1381,050,000o200k–aggregatorlitellm
Claude Haiku 5.5AWS Bedrock–eu-west-10.1100.5500.2200.01100.1381,000,000claude–apiopenrouter
Claude Haiku 5.5AWS Bedrock–us-east-10.1100.5500.2200.01100.1381,000,000claude–apiopenrouter
Claude Haiku 5.5Azure AI Foundry–us0.1100.5500.2200.01100.1381,000,000claude–apiopenrouter
Claude Haiku 5.5Google Vertex AI–europe0.1100.5500.2200.01100.1381,000,000claude–apiopenrouter
Claude Haiku 5.5Google Vertex AI–us0.1100.5500.2200.01100.1381,000,000claude–apiopenrouter
Claude Haiku 5.5AWS Bedrock–apac0.1100.5500.2200.01100.1381,000,000claude–aggregatorlitellm
Claude Haiku 5.5AWS Bedrock–au0.1100.5500.2200.01100.1381,000,000claude–aggregatorlitellm
Claude Haiku 5.5AWS Bedrock–eu0.1100.5500.2200.01100.1381,000,000claude–aggregatorlitellm
Claude Haiku 5.5AWS Bedrock–jp0.1100.5500.2200.01100.1381,000,000claude–aggregatorlitellm
Claude Haiku 5.5AWS Bedrock–us0.1100.5500.2200.01100.1381,000,000claude–aggregatorlitellm
Llama 4 ScoutDeepInfrafp8+priority–0.1500.4500.225––10,000,000llama3–apiopenrouter
Claude Haiku 5.5AWS Bedrock–us-gov-east-10.1200.6000.2400.01200.1501,000,000claude–aggregatorlitellm
Claude Haiku 5.5AWS Bedrock–us-gov-west-10.1200.6000.2400.01200.1501,000,000claude–aggregatorlitellm
Claude Haiku 5.5AWS Bedrock–us-gov0.1200.6000.2400.01200.1501,000,000claude–aggregatorlitellm
DeepSeek V4 FlashMancerfp8–0.1750.5000.2560.175–1,048,576deepseek2026-11-07 ↓apiopenrouter
Mistral Small 4OpenRouter––0.1500.6000.2630.0150–262,144mistral–apiopenrouter
Mistral Small 4Mistral AIzdr–0.1500.6000.2630.0150–262,144mistral–apiopenrouter
Mistral Small 4 3 sourcesMistral AI––0.1500.6000.2630.0150–262,144mistral2026-08-21 ↑apiopenrouter
DeepSeek V4 Flash 2 sourcesAzure AI Foundry––0.1900.5100.2700.0280–1,048,576deepseek–aggregatorlitellm
Qwen3-235B-A22B 2 sourcesDeepInfra––0.1800.5400.270––131,072qwen22026-08-27 ↓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