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 ↑?Batch inBatch outContextTokenizerLast changeConfidence?Source
GPT-6 Astra 2 sourcesOpenAIAWS Bedrock––11.0055.0022.00––1,050,000o200k–aggregatorlitellm
GPT-6 AstraOpenAIAWS Bedrock–us11.0055.0022.00––1,050,000o200k–aggregatorlitellm
Claude Fable 5.1AnthropicAWS Bedrock–eu11.0055.0022.00––1,000,000claude–aggregatorlitellm
Claude Fable 5.1AnthropicAWS Bedrock–us11.0055.0022.00––1,000,000claude–aggregatorlitellm
GPT-6 AstraOpenAIAzure AI Foundry–eu12.0060.0024.00––1,050,000o200k–aggregatorlitellm
Claude Fable 5.1AnthropicAWS Bedrock–us-gov-east-112.0060.0024.00––1,000,000claude–aggregatorlitellm
Claude Fable 5.1AnthropicAWS Bedrock–us-gov-west-112.0060.0024.00––1,000,000claude–aggregatorlitellm
GPT-6.1 Sol 2 sourcesOpenAIOpenAIultrafast–12.0060.0024.00––1,050,000o200k–officialofficial-openai
Claude Fable 5.1AnthropicAWS Bedrock–us-gov12.0060.0024.00––1,000,000claude–aggregatorlitellm
GPT-6 Astra 2 sourcesOpenAIOpenAIfast–20.00100.0040.00––1,050,000o200k–officialofficial-openai
GPT-6 Astra 2 sourcesOpenAIOpenAIultrafast–60.00300.00120.00––1,050,000o200k–officialofficial-openai

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