Back
AI summary
Written by AI from the official notes. Check them for exact details.Inference hooks are now in beta for Claude Enterprise, and Claude Opus 4.1 has been retired.
- Inference hooks allow security server integration for prompt governance.
- Requests are signed and failure handling is configurable.
- Denials are recorded in the compliance Activity Feed.
- Claude Opus 4.1 model has been retired, upgrade recommended.
Why it matters: Claude Enterprise organizations should implement inference hooks for enhanced security and compliance.
Full release notes2 changes
- Inference hooks are now in beta for Claude Enterprise organizations. Point Claude at your organization's AI security server, and each governed prompt across claude.ai, Cowork, and Claude Code is held for the server's allow or deny verdict before inference proceeds. Requests are signed, failure handling is configurable, and every denial is recorded in the compliance Activity Feed. See Inference hooks.
- We've retired the Claude Opus 4.1 model (
claude-opus-4-1-20250805). All requests to this model on the Claude API will now return an error. We recommend upgrading to Claude Opus 5. Researchers can request ongoing access through the External Researcher Access Program.