OpenAIAnthropicGooglexAIPerplexity
← Back to all updatesPublished ·Anthropic• Minor
Anthropic updated prompt caching to automatically read from the longest previously cached prefix when breakpoints are set.
The read
Automatic prefix matching reduces manual overhead for developers managing state across long context windows.
The frame
This change simplifies cost optimization for iterative agent workflows by removing the need for precise cache management.
Primary source
Anthropic →Keep reading
See what Nova3 builds →Related updates
- 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.
- Jun 06, 2026Anthropic released the Models API, Message Batches API, and Token counting API for general availability.
This is the world we build in. It moves this fast. We move with it.
Bring us your project →