feat(server): add /v1/messages/count_tokens endpoint#90
Open
audreyt wants to merge 1 commit into
Open
Conversation
Anthropic's count_tokens API takes the same request shape as /v1/messages
but only returns the prompt token count without running inference. This
short-circuits before enqueueing a job: parse_anthropic_request renders
and tokenizes the prompt the same way it would for a real generation,
then we serialize {"input_tokens": N} and release the request.
Useful for clients that need to plan context budgets before committing
to a generation, e.g. the Anthropic SDK token-counting flow.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Anthropic's count_tokens API takes the same request shape as /v1/messages but only returns the prompt token count without running inference. This short-circuits before enqueueing a job: parse_anthropic_request renders and tokenizes the prompt the same way it would for a real generation, then we serialize {"input_tokens": N} and release the request.
Useful for clients that need to plan context budgets before committing to a generation, e.g. the Anthropic SDK token-counting flow.