xAI released the Context Compaction API to shrink long conversations into shorter context for reuse in follow-up requests.

Reducing token overhead directly lowers costs and improves latency for agents maintaining long state histories.

This tool addresses the performance degradation found in deep conversation loops by optimizing how models process historical data.

• Jun 06, 2026Anthropic updated prompt caching to automatically read from the longest previously cached prefix when breakpoints are set.
• Jun 06, 2026Anthropic optimized prompt caching support in the Message Batches API to improve cache hit rates.
• Jun 06, 2026Anthropic added a delete endpoint to the Message Batches API for managing batch processing tasks.

This is the world we build in. It moves this fast. We move with it.