Document cache_control_injection_points on OpenAI GPT-5.6 targets - #963
Merged
mateo-berri merged 2 commits intoAug 20, 2026
Merged
Conversation
Adds the OpenAI explicit breakpoint mapping that BerriAI/litellm#37628 ships: how injection points become prompt_cache_breakpoint markers plus prompt_cache_options, the per-deployment mode and ttl override, the api.openai.com gate with the prompt_cache_options opt-in for custom api_base deployments, the /v1/responses input_text behavior, and the supports_prompt_cache_breakpoint model map flag.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
Author
|
bugbot run |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
✅ Bugbot reviewed your changes and found no new issues!
Comment @cursor review or bugbot run to trigger another review on this PR
Reviewed by Cursor Bugbot for commit cf7f7d4. Configure here.
Contributor
Author
|
bugbot run |
There was a problem hiding this comment.
✅ Bugbot reviewed your changes and found no new issues!
Comment @cursor review or bugbot run to trigger another review on this PR
Reviewed by Cursor Bugbot for commit cd5e698. Configure here.
mateo-berri
deleted the
litellm_lit5876_openai_prompt_cache_breakpoint_docs
branch
August 20, 2026 17:33
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
TLDR
Problem this solves:
cache_control_injection_pointsdo on OpenAI GPT-5.6 targetsHow it solves it:
prompt_cache_optionsopt-in,/v1/responsesnotesUser Flow
Before: a proxy admin with GPT-5.6 deployments reads the auto-inject tutorial and finds it Anthropic-only
cache_control_injection_pointsdescribed for Anthropic models onlyprompt_cache_breakpointorprompt_cache_optionsopenai/gpt-5.6deployment does anythingAfter: the same pages explain the OpenAI mapping and its limits
prompt_cache_options, and the rules (block-level only, api.openai.com targets,/v1/responsesbehavior,supports_prompt_cache_breakpointflag)prompt_cache_optionsRelevant PRs
Type
📖 Documentation
Note
Cursor Bugbot is generating a summary for commit cf7f7d4. Configure here.