Skip to content

Comments

Enhance Vertex AI context caching documentation#745

Open
mintlify[bot] wants to merge 1 commit intomainfrom
vertex-context-caching-1771339020
Open

Enhance Vertex AI context caching documentation#745
mintlify[bot] wants to merge 1 commit intomainfrom
vertex-context-caching-1771339020

Conversation

@mintlify
Copy link
Contributor

@mintlify mintlify bot commented Feb 17, 2026

Summary

  • Clarifies distinction between Vertex AI's native context caching and Portkey's gateway caching (simple/semantic modes)
  • Notes that context caching is only available for Gemini models on Vertex AI
  • Reorganizes content into two clear use cases:
    1. Using existing context caches with cached_content parameter
    2. Creating new caches via proxy with x-portkey-custom-host header
  • Adds context caching pricing information ($0.000625/token write, $0.00005/token read)

Addresses customer confusion reported in tickets #1340, #2338.

- Clarify distinction from Portkey gateway caching
- Note that context caching is Gemini-specific on Vertex AI
- Reorganize into two use cases: using existing caches and creating new caches
- Add context caching pricing information
- Improve explanation of custom-host proxy pattern for cache creation

Generated-By: mintlify-agent
@anshulbasia27
Copy link

@cursor review this pr for correctness

@cursor
Copy link

cursor bot commented Feb 18, 2026

Skipping Bugbot: Bugbot is disabled for this repository. Visit the Bugbot dashboard to update your settings.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant