Merged
Conversation
dianed-square
changed the title
dianed-square
commented
Jan 10, 2026
| | [xAI](https://x.ai/) | Access to xAI's Grok models including grok-3, grok-3-mini, and grok-3-fast with 131,072 token context window. | `XAI_API_KEY`, `XAI_HOST` (optional) | | ||
|
|
||
| :::tip Prompt Caching for Claude Models | ||
| goose automatically enables Anthropic's [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) when using Claude models via Anthropic, Databricks, OpenRouter, and LiteLLM providers. This adds `cache_control` markers to requests, which can reduce costs for longer conversations by caching frequently-used context. See the [provider implementations](https://github.com/block/goose/tree/main/crates/goose/src/providers) for technical details. |
Contributor
Author
There was a problem hiding this comment.
linked to providers directory to help future proof the list of providers
Contributor
There was a problem hiding this comment.
Pull request overview
This PR documents prompt caching support for Claude models across multiple providers, improving user awareness of this cost-saving feature.
- Adds a tip section explaining that goose automatically enables Anthropic's prompt caching for Claude models
- Clarifies which providers support this feature (Anthropic, Databricks, OpenRouter, and LiteLLM)
- Provides links to Anthropic's documentation and the implementation code
Contributor
|
blackgirlbytes
approved these changes
Jan 10, 2026
zanesq
added a commit
that referenced
this pull request
Jan 12, 2026
…ased * 'main' of github.com:block/goose: chore: break up process agent response (#6348) More 3.7 removal (#6414) CLI show extension errors (#6398) fix[desktop]: Improve UX for ExtensionItem component (#6443) update[doc]: Add tip for GitHub Copilot Provider (#6441) Avoid using cliclack.confirm in non-interactive session (#6412) docs: claude prompt caching note (#6429) Restore task completion notification (#6427) docs: stream-json and auth-token cli options (#6426)
fbalicchia
pushed a commit
to fbalicchia/goose
that referenced
this pull request
Jan 13, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR documents prompt caching which is currently supported by Anthropic, Databricks, OpenRouter, and LiteLLM providers for Claude models
Documentation updates:
documentation/docs/getting-started/providers.md:Type of Change
AI Assistance
Testing
none