mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
Add Google AI Studio (gemini/) and Vertex AI (vertex_ai/) as supported providers for prompt caching. Same cache_control format as Anthropic works - LiteLLM translates it to Google's context caching API under the hood. Includes SDK + proxy examples for both providers. |
||
|---|---|---|
| .. | ||
| my-website | ||