OpenAIAnthropicGooglexAIPerplexity
← Back to all updatesPublished ·Anthropic• Minor
Anthropic updated Messages API rate limits to separate input and output tokens and added tool use to Workbench.
The read
Separating input and output limits allows for more precise cost and capacity management during high volume long context operations.
The frame
Testing tool definitions in the Workbench environment reduces the friction of moving agentic workflows from prototype to production.
Primary source
Anthropic →Keep reading
See what Nova3 builds →Related updates
- 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.
Bring us your project →