Skip to main content
GitHub Copilot Chat in VS Code can bring your own key. Lyceum connects through its Custom Endpoint provider.

Configure

1

Open the Language Models editor

Run Chat: Manage Language Models from the command palette, or click the gear icon in the chat model picker.
2

Add a custom endpoint

Choose Add Models → Custom Endpoint, and set the API type to Chat Completions.
3

Fill in the fields

4

Pick the model

Select it from the model picker in the Copilot Chat panel.

Two Lyceum-specific details

Copilot is stricter than most clients, so two things differ from the other pages here.
Use slash-free model IDs. Copilot rejects / in custom model names. Every Lyceum model has a slash-free alias. Replace each / with -:Both forms resolve to the same model; the alias is resolved before any model lookup.
Prefer z-ai-glm-5.2-instant over z-ai-glm-5.2. GLM 5.2 is a reasoning model and returns its trace in the non-standard reasoning_content field. Copilot cannot pass request parameters to turn that off, and it caps max_tokens, so the reasoning can consume the whole output budget and the reply arrives empty. The -instant variant is the same model with thinking disabled, which is what you want here.

Anthropic mode

Copilot’s Custom Endpoint also speaks the Anthropic Messages API. To use Lyceum that way instead, set the API type to Messages and point it at: See Claude Code for the full list of claude-* model aliases.

Copilot CLI

The Copilot CLI works with Lyceum without a GitHub sign-in. Install it with npm install -g @github/copilot, set 3 variables, and give it a task: Run copilot without -p for an interactive session. To use the Responses API, also set COPILOT_PROVIDER_WIRE_API=responses.

Web pages

Copilot Chat and the Copilot CLI read pages with their fetch tools, which run on your machine and work with Lyceum models. Copilot can’t add the request field that turns on Lyceum’s web search. For web search with Lyceum models, use Codex, where it works with nothing to set up.

What works with BYOK

Models must support tool calling to appear in the agent-mode picker. All models recommended on these pages do.