Inference hooks
BetaVerifiedAdded Sep 22, 2026
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.
Topics: LLMs, Governance, Security, Coding agents
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More Claude Platform releases
Every Claude Platform release| Date | Release | Type |
|---|---|---|
| Aug 5 | Claude Opus 4.1 is retired on the Claude API Deprecation | Deprecation |
| Aug 7 | Claude Managed Agents sessions support hard spend budgets Pricing | Pricing |
| Aug 7 | Claude Managed Agents sessions can consult an advisor model Update | Update |
| Aug 7 | Claude Managed Agents adds inference_geo to control where inference runs Update | Update |
| Aug 7 | Claude Managed Agents sessions load skills from GitHub repositories Update | Update |
| Aug 3 | Compliance API returns cloud Cowork session transcripts in beta Beta | Beta |
| Aug 1 | Dreams research preview adds support for Claude Opus 5 Preview | Preview |
| Aug 10 | Claude Sonnet 5 introductory pricing of $2 / $10 per MTok becomes permanent Pricing | Pricing |
