LibreChat - ScitiX

LibreChat is an open-source, self-hosted ChatGPT-style UI supporting many providers. It reaches the ScitiX Model Inference API through its custom endpoints feature, configured in librechat.yaml. Default model here is glm-5.2; see the Models page for the full list and pricing. Deploy LibreChat per the official guide.

Configure

Providers in LibreChat are defined server-side in librechat.yaml, not in the UI. Create an API key on the ScitiX API Keys page, then add ScitiX as a custom endpoint:

version: 1.2.1
cache: true
endpoints:
  custom:
    - name: "ScitiX"
      apiKey: "${SCITIX_API_KEY}"
      baseURL: "https://api.scitix.ai/model-api/v1"
      models:
        default:
          - "glm-5.2"
        fetch: false
      titleConvo: true
      titleModel: "glm-5.2"
      modelDisplayLabel: "ScitiX"

Field	Value
`name`	Label shown in the endpoint selector, e.g. `ScitiX`
`apiKey`	`${SCITIX_API_KEY}` — resolved from the environment at request time
`baseURL`	ScitiX OpenAI-compatible endpoint: `https://api.scitix.ai/model-api/v1`
`models.default`	ScitiX model IDs to offer, e.g. `glm-5.2`. Pick a model with native tool calling for LibreChat’s agent/tool features.
`models.fetch`	`false` — ScitiX does not expose OpenAI’s `/models` list format, so list models here instead of fetching

Pass the key in the environment LibreChat reads (its .env, or the container env). Make sure the config file is picked up (CONFIG_PATH=/path/to/librechat.yaml, or the default ./librechat.yaml):

SCITIX_API_KEY=<Your API Key>

Verify

Restart LibreChat, sign in, and open a new chat. In the top-left endpoint selector choose ScitiX (model glm-5.2), send a message — a normal reply confirms the connection.

LibreChat replying via the ScitiX endpoint on glm-5.2

LibreChat has no UI to add a custom provider, so the ScitiX endpoint must be defined in the config file, not the settings screen. Verified on LibreChat v0.8.7.