Anthropic has ended the research preview of Claude Opus 5.5's Fast Mode and removed the waitlist, opening it to all developers, according to 36Kr and AIbase. The reports say Fast Mode keeps the same model weights and reasoning capability as the standard version and instead optimizes API and inference configuration to raise output speed up to 2.5x — a vendor-stated figure with no independent measurement supplied. Developers enable it with a speed: "fast" API parameter or the /fast toggle in Claude Code; it currently covers Opus 5.5, Opus 5 and Opus 4.8 but not Sonnet or Haiku, and is available on the API and Microsoft Azure Foundry, with Google Cloud coming and AWS Bedrock unsupported for now. 36Kr also reports lower pricing — $8 input / $40 output per million tokens for Opus 5.5 Fast Mode versus $10/$50 for Opus 5 and Opus 4.8 Fast Mode — plus separate rate limits, no prompt-cache sharing with standard mode, automatic fallback to standard speed at the cap, and billing against a separate usage allowance for subscribers.