xAI released the Context Compaction API to shrink long conversations into shorter context for reuse.

This reduces input costs and latency for long agent loops by maintaining focus on relevant data.

The tool provides a native method to manage token limits and response speed in complex multi-turn operations.

• 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.