# Inferris

> Inferris serves open models (today: glm-5.3) over OpenAI- and Anthropic-compatible APIs at https://api.inferris.ai, priced per token, run from Singapore. Any agent harness that lets you set a base URL can use it.

The web app at https://inferris.ai is a JavaScript single-page app. The files below are plain text and readable without JavaScript.

## API

- [API page (Markdown)](https://inferris.ai/developers.md): base URLs, auth, model ID, endpoints, copy-paste setup for Claude Code, Codex CLI, OpenCode and OpenAI-compatible tools, SDK examples, errors and retries
- [Agent setup](https://inferris.ai/agents.md): short instructions for an agent configuring itself to use Inferris

## Optional

- [API page](https://inferris.ai/developers): the same content for people
- [Docs](https://inferris.ai/docs): quickstart, models, pricing, rate limits, errors
- [Models and pricing](https://inferris.ai/pricing)
- [Status](https://inferris.ai/status)
- [Research](https://inferris.ai/research): methods and write-ups, including the serving architecture