We've rolled out cache-aware rate limits in the Anthropic API. This means that prompt cache read tokens will no longer count against your input token per minute rate limits.
Anthropic API Introduces Cache-Aware Rate Limits for Prompt Cache
By
–
Global AI News Aggregator
By
–
We've rolled out cache-aware rate limits in the Anthropic API. This means that prompt cache read tokens will no longer count against your input token per minute rate limits.
Leave a Reply