Skip to main content
Point Claude Code at Lyceum’s inference endpoint to use it with any of our supported models — and switch between them mid-session with /model, no restart needed.

​
Setup

The recommended way is the Lyceum CLI. lyceum code launches Claude Code preconfigured, in its own profile that never touches an existing Anthropic login: 
pip install https://lyceum.technology/downloads/lyceum_cli-1.0.53-py3-none-any.whl
lyceum auth login --api-key lk_<your_api_key>   # one-time
lyceum code
Get your API key from the dashboard. (Temporary install URL until lyceum-cli is republished under its normal name on PyPI — check pip install lyceum-cli first, in case it’s caught up by the time you read this.) Trying it out in a single terminal without installing anything? Set these two environment variables before starting Claude Code: 
export ANTHROPIC_BASE_URL=https://api.lyceum.technology/api/v2/external/claude
export ANTHROPIC_API_KEY=lk_<your_api_key>
claude
Or write the same two values into ~/.claude/settings.json yourself for a setup that persists across terminals: 
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.lyceum.technology/api/v2/external/claude",
    "ANTHROPIC_API_KEY": "lk_<your_api_key>"
  }
}
Prefer a one-line script that does the settings.json edit for you? Run: 
curl -fsSL https://lyceum.technology/install-claude.sh | sh -s -- lk_<your_api_key>
claude

​
Switching models mid-session

Pass any Lyceum model ID directly to /model inside Claude Code: 
/model z-ai/glm-5.2
/model moonshotai/kimi-k2.6
/model deepseek/deepseek-v4-pro
The switch takes effect with your next message — no restart, your conversation context stays. Any model from the serverless catalog works. IDs are case-insensitive, and slash-free variants (z-ai-glm-5.2) are accepted for clients that reject / in model names. Note: the bare /model menu (without an argument) only lists Anthropic tier names — selecting there switches between the tiers mapped below, not the full catalog.

​
Model mapping

Anthropic tier names map to Lyceum models automatically:
Claude tierModel
claude-fable-* / claude-opus-*GLM-5.2
claude-sonnet-*Kimi-K2.7-Code
claude-haiku-*MiniMax-M3
Model selection precedence, highest first:
  1. A Lyceum model ID in the request’s model field (what /model <id> sends)
  2. A fixed-model endpoint path as the base URL, e.g. .../external/claude-kimi or .../external/claude-deepseek
  3. The tier mapping above

​
Switching from Anthropic to Lyceum

If you previously used Claude Code with a direct Anthropic key, make sure to update both variables - not just the base URL. Claude Code warns you if both a claude.ai session and ANTHROPIC_API_KEY are set at the same time. To avoid auth conflicts, run /logout inside Claude Code before setting the Lyceum key, or use lyceum code, which runs in a separate profile.

​
Note on 1M context models

Avoid using sonnet[1m] or similar extended-context variants. The [1m] suffix is Anthropic-specific and Claude Code will not connect through the proxy with it set. Use sonnet instead, either via /model in Claude Code or by setting "model": "sonnet" in ~/.claude/settings.json.