Connect LibreChat

Merge an OpenAI-compatible endpoint into LibreChat's YAML configuration and discover available text models.

AELDER · SERVICE BASE URL

https://aelder.dev/v1

LOCAL CONFIGURATION

Let my agent set this up

Copy this task to an agent already running on your computer. Enter your API key locally when asked.

Help me connect LibreChat to AELDER using this guide: https://aelder.dev/docs/librechat/
Service Base URL: https://aelder.dev/v1
First inspect my installed version, active profile and configuration. Explain any mismatch with the guide before changing anything.
Use the documented local configuration or CLI method. Do not automate the GUI, install software or change permissions without asking.
Preserve existing accounts, providers, models, defaults, permissions and unrelated settings. Propose the smallest change, show a redacted diff, and back up any files before editing.
Have me enter my API key locally using the tool's secret storage or an environment variable. Never ask me to paste a key into chat, print it, or include it in a command, diff, log or commit.
Use the exact model ID I choose from my account's model list. Do not invent model IDs or assume every model supports every API format or tool feature.
Validate syntax and configuration loading before making any generation request. If there is no dry-run, say so.
Explain any proposed paid test, the model and what it sends, and ask for approval before running it. Do not send project files or private conversation history as a test.
Finish with the settings changed, checks performed and steps to restore the backup.

Use this on an existing LibreChat installation you administer. It adds a named OpenAI-compatible Chat Completions endpoint. Back up the affected files and merge the fragments into existing mappings and lists.

1. Add the endpoint

In the installation’s librechat.yaml, append an entry under endpoints.custom:

endpoints:
  custom:
    - name: my-api
      apiKey: '${SERVICE_API_KEY}'
      baseURL: '${SERVICE_BASE_URL}'
      models:
        default: ['YOUR_MODEL_ID']
        fetch: true
      titleConvo: false
      modelDisplayLabel: my-api

Replace YOUR_MODEL_ID with an exact ID from the authenticated models endpoint. Keep the file’s existing version and other endpoints. Do not add provider: anthropic for this Chat Completions setup, including when the selected model is a Claude model.

Set SERVICE_BASE_URL in LibreChat’s private .env to the service Base URL above, including /v1. Set SERVICE_API_KEY privately in the same file or your deployment’s secret environment. Do not append /chat/completions to the URL or put a real key into YAML, shell history or a setup chat. Keep .env out of version control.

This configuration shares the configured service key with users who can use the endpoint. To require each user’s own key instead, use apiKey: user_provided and let them enter it privately in LibreChat’s UI.

2. Check the Docker mount

For Docker, ensure your existing docker-compose.override.yml mounts the file. Merge this volume if it is absent:

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

Skip this for a local non-Docker installation. Preserve existing volumes, environment settings and access controls.

3. Restart and select the endpoint

Restart LibreChat using your existing deployment method so it reads the configuration. For an existing Compose deployment, run from its project directory:

docker compose up -d --force-recreate api

Open a new conversation, select my-api, and select a discovered text model. fetch: true loads the catalog; the default list supplies the initial selection.

Send a short message, which spends balance, and check your service dashboard. If the endpoint appears but fails, confirm that .env defines SERVICE_BASE_URL, the file is mounted, and the selected model is allowed by the key. Chat success does not verify LibreChat Agents or every tool integration.

See LibreChat’s official custom endpoint setup and endpoint configuration reference.

Need the key? Open your AELDER dashboard. For direct API calls, see the API reference.