We’ve deprecated fast mode for Claude Opus 4.8, with removal on November 30, 2026
By Steven Van ·
Requests to claude-opus-4-8 with speed "fast" will error after removal, and Claude Opus 5.5 supports fast mode with no beta header.
Fast mode for Claude Opus 4.8 is deprecated, and Anthropic will remove it on November 30, 2026. After that date, requests to claude-opus-4-8 with speed: "fast" will return an error.
Keeping fast mode
Fast mode continues on Claude Opus 5.5, which Anthropic names as the migration target. On Claude Opus 5.5, fast mode is set with speed: "fast" on the request and needs no beta header. Fast mode is not available on Claude Opus 4.7, where such requests return an error.
Other differences when moving from Opus 4.8
The migration guide lists several changes between Anthropic's Opus 4.8 and Opus 5.5:
- A request with no thinking field now runs with thinking. On Opus 4.8, thinking is off unless requested.
- The minimum cacheable prompt length drops from 1,024 tokens to 512 tokens.
- Priority Tier is not supported on Opus 5.5, while Opus 4.8 keeps it. Organisations with a Priority Tier commitment need to plan capacity separately.
The guide also suggests, as optional, trying task budgets (beta, with the task-budgets-2026-03-13 header) for agentic workloads and mid-conversation tool changes (beta) to keep prompt cache hits when tools change.