LibreChat

A self-hosted multi-model chat UI that takes Tium as a custom endpoint.

Setup

Point LibreChat at Tium

You need the base URL https://api.tium.ai/v1 and an API key from your dashboard. Keys are shown once at creation.

  1. 1.Add the endpoint to librechat.yaml

    Custom endpoints live under endpoints.custom. Add the block above alongside any others you already run.

    librechat.yaml
    endpoints:
      custom:
        - name: 'Tium'
          apiKey: '${TIUM_API_KEY}'
          baseURL: 'https://api.tium.ai/v1'
          models:
            default: ['glm-5.3-flash']
            fetch: true
          titleConvo: true
          modelDisplayLabel: 'Tium'
  2. 2.Put the key in your environment

    The ${...} form reads TIUM_API_KEY from the environment rather than storing the key in the config. Set it to 'user_provided' instead if you want each person to supply their own.

Worth knowing

What LibreChat gets wrong

Tool-specific behaviour that surprises people, and what to do about it.

fetch: true keeps the model list current

LibreChat can read the catalog from GET /v1/models rather than using the default list, so new models appear without a config edit. The default array stays as the fallback for when that call fails.

baseURL keeps its /v1 and nothing more

LibreChat appends /chat/completions to the base URL itself unless directEndpoint is set, so the value above is complete as written.

Elsewhere

Other tools

The same base URL and key work anywhere that takes an OpenAI-compatible endpoint.