Skip to main content
Every AI coding tool that speaks the OpenAI or Anthropic API works with Lyceum. You point it at our endpoint, give it your API key, and pick a model. Get a key from the dashboard. See API keys for scopes and rotation.

Which endpoint

Two endpoints, depending on what the tool speaks: Most tools want the first. Claude Code wants the second. Codex uses the Responses API on the first.

Pick your tool

Claude Code

CLI and VS Code extension

Codex

OpenAI’s terminal agent, on the Responses API

Cursor

Model override in settings

opencode

Custom provider block

GitHub Copilot

Custom endpoint in VS Code

Cline

VS Code agent

Kilo Code

VS Code agent

Zed

Editor with built-in agent

aider

Terminal pair programmer

goose

Block’s terminal agent

Hermes Agent

Nous Research’s terminal agent
Building your own agent in TypeScript? See the Vercel AI SDK guide.

Verify before you configure

If a tool misbehaves, check the API directly first. This is the same request every tool above makes: List every model your key can reach:

Choosing a model

Full list at active models, or call /models above.
Model IDs are case-insensitive. Tools that reject / in model names accept the slash-free form, so z-ai-glm-5.2 resolves to z-ai/glm-5.2.

Context windows

The /models response lists each model’s context_length and max_output_tokens. Some tools don’t read them and ask you to set Context Window and Max Output Tokens by hand (Cline, Kilo Code, Zed). Take the numbers from the /models response or the models page. Lyceum can search the web while a model answers, and the answer cites its sources. See which coding tools can use web search and how to turn it on in each.