Skip to content

Rewrite the README for the current token-count API - #3

Merged
guuzaa merged 1 commit into
mainfrom
cursor/readme-v41-cef6
Oct 11, 2026
Merged

guuzaa merged 1 commit into
mainfrom
cursor/readme-v41-cef6

Conversation

@guuzaa

@guuzaa guuzaa commented Oct 11, 2026

Copy link
Copy Markdown
Owner

Summary

Rewrites README.md so it matches the worker after the latest main: one model family, the fields it actually reads, and the errors, caps, and auth behavior in src/ and wrangler.toml.

The quick-start counts were checked against pnpm dev:

  • {"model":"deepseek-flash","messages":[{"role":"user","content":"Hello"}]} → {"data":{"total_tokens":31}}
  • the same message with "thinking":{"type":"disabled"} → {"data":{"total_tokens":5}}

Field names that overlap the chat completions API link to the official docs instead of copying them. Chat-completion fields this endpoint ignores or rejects are called out.

Docs only. No code changes.

Open in Web Open in Cursor 

Describe the fields, defaults, errors, and limits the worker actually
implements, with curl examples checked against a local dev server.

Co-authored-by: Jowell Young <guza@duck.com>
@guuzaa
guuzaa marked this pull request as ready for review October 11, 2026 06:26
@guuzaa
guuzaa merged commit c60f777 into main Oct 11, 2026
1 check passed
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.

2 participants