Ability to pass in custom headers that are sent alongside LLM requests to a Claude proxy

Resolved 💬 3 comments Opened Mar 4, 2025 by jonastemplestein Closed Mar 17, 2025

Our specific use case is to pass in a cache key to our caching LLM proxy so we can cache identical requests during eval runs

View original on GitHub ↗

This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗