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

ModelVendorHostVariantRegionInputOutputBlended ↑?Cache readCache writeContextTokenizerLast changeConfidence?Source
Claude Opus 5.5AnthropicPerplexity––4.0020.008.000.200–1,000,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicAWS Bedrock–global4.0020.008.000.2005.001,000,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicDeepInfra––4.0020.008.000.200–1,000,000claude–officialofficial-deepinfra
Nano Banana 2.1GoogleGoogle Vertex AI––1.5030.008.630.150–65,536gemini–aggregatormodelsdev
Claude Opus 5.5AnthropicAWS Bedrock–eu-west-14.4022.008.800.2205.501,000,000claude–apiopenrouter
Claude Opus 5.5AnthropicAWS Bedrock–us-east-14.4022.008.800.2205.501,000,000claude–apiopenrouter
Claude Opus 5.5AnthropicAzure AI Foundry–us4.4022.008.800.2205.501,000,000claude–apiopenrouter
Claude Opus 5.5AnthropicGoogle Vertex AI–us4.4022.008.800.2205.501,000,000claude–apiopenrouter
Claude Opus 5.5AnthropicGoogle Vertex AI–europe4.4022.008.800.2205.501,000,000claude–apiopenrouter
Claude Opus 5.5AnthropicAWS Bedrock–apac4.4022.008.800.2205.501,000,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicAWS Bedrock–au4.4022.008.800.2205.501,000,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicAWS Bedrock–eu4.4022.008.800.2205.501,000,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicAWS Bedrock–jp4.4022.008.800.2205.501,000,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicAWS Bedrock–us4.4022.008.800.2205.501,000,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicAWS Bedrock–us-gov-east-14.8024.009.600.2406.001,000,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicAWS Bedrock–us-gov-west-14.8024.009.600.2406.001,000,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicAWS Bedrock–us-gov4.8024.009.600.2406.001,000,000claude–aggregatorlitellm
Claude Opus 4.5AnthropicOpenRouter––5.0025.0010.000.5006.25200,000claude–apiopenrouter
GPT-6 Astra 2 sourcesOpenAIOpenAIflex–5.0025.0010.000.5006.251,050,000o200k–officialofficial-openai
Claude Opus 4.5AnthropicClaude on AWS––5.0025.0010.000.5006.25200,000claude–apiopenrouter
Claude Opus 4.5AnthropicAzure AI Foundry–global5.0025.0010.000.5006.25200,000claude–apiopenrouter
Claude Opus 4.5AnthropicGoogle Vertex AI–global5.0025.0010.000.5006.25200,000claude–apiopenrouter
Claude Opus 4.5 3 sourcesAnthropicAWS Bedrock––5.0025.0010.000.5006.25200,000claude2026-09-23 ↑apiopenrouter
Claude Opus 4.5 4 sourcesAnthropicAnthropic––5.0025.0010.000.5006.25200,000claude–officialofficial-anthropic
Claude Opus 4.5 2 sourcesAnthropicAzure AI Foundry––5.0025.0010.000.5006.25200,000claude–aggregatorlitellm
Claude Opus 4.5AnthropicPerplexity––5.0025.0010.000.500–200,000claude–aggregatorlitellm
Claude Opus 4.5 2 sourcesAnthropicGoogle Vertex AI––5.0025.0010.000.5006.25200,000claude–aggregatorlitellm
GPT-Rosalind Research 2 sourcesOpenAIOpenAI––5.0025.0010.000.500––––officialofficial-openai
GPT-6 AstraOpenAIOpenAIbatch–5.0025.0010.000.5006.251,050,000o200k–officialofficial-openai
Claude Opus 4.5AnthropicAWS Bedrock–global5.0025.0010.000.5006.25200,000claude–aggregatorlitellm
GPT-Rosalind Discovery 2 sourcesOpenAIOpenAI––5.0025.0010.000.500––––officialofficial-openai
Claude Opus 4.5AnthropicAWS Bedrock–eu-west-15.5027.5011.000.5506.88200,000claude–apiopenrouter
Claude Opus 4.5AnthropicAWS Bedrock–eu5.5027.5011.000.5506.88200,000claude–aggregatorlitellm
Claude Opus 4.5AnthropicAWS Bedrock–us5.5027.5011.000.5506.88200,000claude–aggregatorlitellm
Claude Opus 5.5AnthropicAnthropicfast–8.0040.0016.000.40010.001,000,000claude–apiopenrouter
GPT-6 AstraOpenAIOpenRouter––10.0050.0020.001.0012.501,050,000o200k–apiopenrouter
Claude Fable 5.1AnthropicOpenRouter––10.0050.0020.000.25012.501,000,000claude–apiopenrouter
GPT-6 Astra 3 sourcesOpenAIAzure AI Foundry––10.0050.0020.001.0012.501,050,000o200k2026-09-29 ↑apiopenrouter
GPT-6 Astra 4 sourcesOpenAIOpenAI––10.0050.0020.001.0012.501,050,000o200k–officialofficial-openai
Claude Fable 5.1 3 sourcesAnthropicAzure AI Foundry––10.0050.0020.000.25012.501,000,000claude–apiopenrouter
Claude Fable 5.1 4 sourcesAnthropicAnthropic––10.0050.0020.000.25012.501,000,000claude–officialofficial-anthropic
Claude Fable 5.1 3 sourcesAnthropicAWS Bedrock––10.0050.0020.000.25012.501,000,000claude–apiopenrouter
Claude Fable 5.1AnthropicGoogle Vertex AI–global10.0050.0020.000.25012.501,000,000claude–apiopenrouter
Claude Fable 5.1 2 sourcesAnthropicGoogle Vertex AI––10.0050.0020.000.25012.501,000,000claude–aggregatorlitellm
Claude Fable 5.1AnthropicPerplexity––10.0050.0020.000.250–1,000,000claude–aggregatorlitellm
GPT-6 Astra 2 sourcesOpenAIAWS Bedrock–global10.0050.0020.001.0012.501,050,000o200k–apiopenrouter
Claude Fable 5.1AnthropicAWS Bedrock–global10.0050.0020.000.25012.501,000,000claude–aggregatorlitellm
GPT-6 AstraOpenAIPerplexity––10.0050.0020.001.0012.501,050,000o200k–aggregatorlitellm
GPT-6 AstraOpenAIAWS Bedrock–us-west-211.0055.0022.001.1013.751,050,000o200k–apiopenrouter
GPT-6 Astra 2 sourcesOpenAIAzure AI Foundry–us11.0055.0022.001.1013.751,050,000o200k–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