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 ↑?ContextTokenizerConfidence?
GPT-6 Astra 2 sourcesAWS Bedrock––11.0055.0022.001,050,000o200kaggregator
GPT-6 AstraAWS Bedrock–us11.0055.0022.001,050,000o200kaggregator
Claude Fable 5.1AWS Bedrock–eu11.0055.0022.001,000,000claudeaggregator
Claude Fable 5.1AWS Bedrock–us11.0055.0022.001,000,000claudeaggregator
GPT-6 AstraAzure AI Foundry–eu12.0060.0024.001,050,000o200kaggregator
Claude Fable 5.1AWS Bedrock–us-gov-east-112.0060.0024.001,000,000claudeaggregator
Claude Fable 5.1AWS Bedrock–us-gov-west-112.0060.0024.001,000,000claudeaggregator
GPT-6.1 Sol 2 sourcesOpenAIultrafast–12.0060.0024.001,050,000o200kofficial
Claude Fable 5.1AWS Bedrock–us-gov12.0060.0024.001,000,000claudeaggregator
GPT-6 Astra 2 sourcesOpenAIfast–20.00100.0040.001,050,000o200kofficial
GPT-6 Astra 2 sourcesOpenAIultrafast–60.00300.00120.001,050,000o200kofficial

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