docs: Inference Providers integration guide billing#2583
Merged
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Note
Low Risk
Markdown-only changes to provider onboarding docs; no runtime or billing code is modified.
Overview
Expands the Billing section in
register-as-a-provider.mdso inference partners can implement and operate the cost callback API with clearer expectations.Adds How billing works (placeholder usage → minute polling → real cost replacement) and stresses that users are only charged after the provider returns a cost.
Documents billing API response rules (partial batches,
{ "requests": null }, ignore unknown IDs), Price unit edge cases (0, round-up, invalid values), Timing and retries (1-minute batches, optional delay, idempotency, ~30-minute give-up with no user charge), and Which requests we ask about (2xx/3xx only). Also requires the billing Inference-Id (or equivalent) header on every response, including streaming.Reviewed by Cursor Bugbot for commit 2a01fc5. Bugbot is set up for automated code reviews on this repo. Configure here.