docs: add OpenZoo LLM provider guide - #773
Open
staccDOTsol wants to merge 2 commits into
Open
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Updated 2026-09-02: corrected — the hosted
https://api.openzoo.fun/v1endpoint answers HTTP 402 to a plain OpenAI client (it only serves calls that pay x402 or carry an OpenZoo subscription key,ozk_live_…). The page now sets up the localnpx openzooproxy (http://localhost:8402/v1), which pays x402 per call from a local burner wallet and ignores the API key.Your llms.mdx overview invites provider setup PRs from people who've run OpenHands against a provider — this adds a guide for OpenZoo: new page under
openhands/usage/llms/, nav entry indocs.json, and a link in the llms.mdx provider list.OpenZoo is OpenAI-compatible with no signup: a local
npx openzooproxy pays per call over x402 and ignores the API key, so the Advanced-settings table on the page is runnable as-is once the proxy is up (Custom Modelopenai/<id>, Base URLhttp://localhost:8402/v1, orhttp://host.docker.internal:8402/v1from Docker). The model list at/v1/modelsis free to fetch. The hosted endpoint is mentioned only as needing x402 or a subscription key.Disclosure: I operate OpenZoo.
🤖 Generated with Claude Code