Back
AI summary
Written by AI from the official notes. Check them for exact details.The Context Compaction API is now available for optimizing long conversations.
- Shrink long conversations into shorter context
- Reuse compacted context in follow-up requests
- Lower cost and faster response times
- Improved sharpness of responses on long agent loops
Why it matters: Users managing long conversations should adopt this feature for better efficiency and cost savings.
Full release notes
The Context Compaction API is now available. You can shrink long conversations into a shorter context and reuse it in follow-up requests for lower cost, faster time-to-first-token, and sharper responses on long agent loops. For more details, see the Context Compaction docs.