← All applications · Connect apps section on /docs
OpenAIManual setup
LibreChat
LibreChat: configure a provider for a self-hosted chat interface.
Published instructions · App version: unverified
Chat, ping, invoke and content-generation examples may send real billable requests. Check the model, balance, rate and minimum before running them. GET /v1/models checks authentication and the catalogue only. Set up environment variables safely
Base URL to paste
OpenAI SDKs generally use a URL ending in /v1; Anthropic SDKs use the root URL. Avoid adding /v1 twice. Protocol compatibility does not guarantee every provider feature.
https://thapi.cloud/v1Prerequisites
- LibreChat is deployed
- STALI_API_KEY environment variable on the server
Recommended model: claude-fable-5
Quick way — command / config
version: 1.2.8
endpoints:
custom:
- name: "ThAPI"
apiKey: "${STALI_API_KEY}"
baseURL: "https://thapi.cloud/v1"
models:
default: ["claude-fable-5", "claude-sonnet-5", "gpt-5.6-sol"]
fetch: true
titleConvo: true
titleModel: "claude-fable-5"
modelDisplayLabel: "ThAPI"Where to place file / fill Settings
Filelinux
librechat.yaml (thư mục cài LibreChat)
Add a custom endpoint as shown in the snippet; restart the container/service after editing.
Filewindows
librechat.yaml trong thư mục deploy
Same as Linux; ensure the STALI_API_KEY environment variable is present in docker-compose.
Verify connection
- Select the ThAPI endpoint in the UI
- Send a test message
Troubleshooting
| Symptom | Reason | How to handle |
|---|---|---|
| fetch models fail | Incorrect baseURL or a firewall issue. | curl https://thapi.cloud/v1/models -H "Authorization: Bearer sk-thapi-..." |