LibreChat

OverviewCopy Anchor Link

Add TokenLab to LibreChat as a custom OpenAI-compatible endpoint.

EnvironmentCopy Anchor Link

Add this variable to the .env file in your LibreChat project root:

TOKENLAB_API_KEY=sk-your-tokenlab-key

Example EndpointCopy Anchor Link

In the LibreChat project root, create librechat.yaml from librechat.example.yaml if needed. Keep its required version and existing settings, then merge this entry into endpoints.custom:

endpoints:
  custom:
    - name: 'TokenLab'
      apiKey: '${TOKENLAB_API_KEY}'
      baseURL: 'https://api.tokenlab.sh/v1'
      models:
        default:
          - 'gpt-5.5'
          - 'gpt-5.6-terra'
          - 'gpt-5.6-luna'
          - 'claude-opus-4-8'
          - 'claude-sonnet-5'
          - 'gemini-3.5-flash'
          - 'deepseek-v4-pro'
          - 'deepseek-v4-flash'
        fetch: true
      titleConvo: true
      titleModel: 'gpt-5.6-luna'
      modelDisplayLabel: 'TokenLab'

For Docker, mount this file as /app/librechat.yaml in the API container. Restart the same LibreChat deployment and select TokenLab. See LibreChat's setup guide.

NotesCopy Anchor Link

LibreChat uses the OpenAI-compatible chat path for this setup. TokenLab also exposes native Responses, Anthropic Messages, and Gemini-compatible endpoints for clients that support those request shapes.