Skip to main content
LibreChat is a self-hosted, ChatGPT-style web interface with support for many providers. RuAPI is added as a custom endpoint in librechat.yaml — after that, all RuAPI models show up in the model picker.

​
Prerequisites

1

RuAPI account and API key

Console → Tokens → create an sk-... key. The balance tops up in USDT — see Top-up.
2

A running LibreChat

Install per the LibreChat docs (usually Docker).

​
Setup

1

Add the key to .env

RUAPI_KEY=sk-YOUR_KEY
2

Describe the endpoint in librechat.yaml

endpoints:
  custom:
    - name: "RuAPI"
      apiKey: "${RUAPI_KEY}"
      baseURL: "https://www.ruapi.ai/v1"   # with /v1
      models:
        default: ["claude-opus-4-8"]        # exact names on the pricing page
        fetch: true                          # pull the full catalog via /v1/models
      titleConvo: true
      titleModel: "claude-opus-4-8"
3

Restart LibreChat

Reload the config (restart the container). A RuAPI provider appears in the UI.
fetch: true pulls the model list automatically via /v1/models. If you’d rather not auto-list, drop fetch and list the IDs you want in default.

​
Verify

In the UI, pick the RuAPI provider and a model, then send a message. A reply plus an entry in RuAPI Console → Logs confirms the wiring.

​
Troubleshooting

  • Check the indentation in librechat.yaml (YAML is whitespace-sensitive) and that the block sits under endpoints.custom.
  • Make sure the container reloaded the config after your edits.
  • baseURL must be https://www.ruapi.ai/v1 with /v1.
  • The RUAPI_KEY in .env must hold the RuAPI token (sk-...), and apiKey must reference it via ${RUAPI_KEY}.
Check titleConvo: true and that titleModel points to an available model.