OpenAI moved model selection and thinking effort controls into the composer for web users on paid plans.

Consolidating model switching and reasoning depth at the prompt level reduces friction for multi-model workflows.

This change responds to the need for granular control over compute costs and reasoning time during active sessions.

• 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.