LibreChat

LibreChat adds UberLLM as a custom endpoint in librechat.yaml.

Before you start

• An UberLLM account with credit, and an API key from Dashboard → Keys (ull_...).

1. Add the key to .env

UBERLLM_API_KEY=ull_your-key-here

2. Add the endpoint to librechat.yaml

If the file already has an endpoints.custom list, paste only the - name: entry into it, with the same indentation.

version: 1.3.18
endpoints:
  custom:
    - name: "UberLLM"
      apiKey: "${UBERLLM_API_KEY}"
      baseURL: "https://api.uberllm.dev/v1"
      models:
        default: ["deepseek/deepseek-v4.1-flash", "z-ai/glm-5.2", "moonshotai/kimi-k3", "google/gemini-2.5-flash"]
        fetch: true
      titleConvo: true
      titleModel: "qwen/qwen3-vl-235b-a22b-instruct"
      modelDisplayLabel: "UberLLM"
      iconURL: "https://uberllm.dev/apple-icon"
      headers:
        X-Title: "LibreChat"

• fetch: true loads every chat model from /v1/models (about 250). For a short menu, set fetch: false and list the models you want in default.
• titleModel is a fast model that answers without a reasoning step, so chat titles come back short.
• To let each user enter their own key in the LibreChat screen, write apiKey: "user_provided" (no ${}).

3. Mount the file (Docker)

Create docker-compose.override.yml next to docker-compose.yml:

services:
  api:
    volumes:
      - type: bind
        source: ./librechat.yaml
        target: /app/librechat.yaml

Then restart: docker compose down && docker compose up -d.

Recommended models

Checked on 2026-10-30: each one streamed an answer through UberLLM.

Common errors