How to use Netra Runtime with Open WebUI

What you need

• Open WebUI running (typically via Docker) with admin access; the Open WebUI docs cover installation.
• A Netra Runtime API key from your dashboard at app.netraruntime.com. The API base URL is https://api.netraruntime.com/v1 (self-hosted deployments use their own endpoint URL instead).

Step 1: add the connection

Open the Admin Panel → Settings → Connections, and under OpenAI API add a connection:

Save, and Open WebUI queries the connection's models endpoint. Every model your Netra deployment serves appears in the model picker automatically; there is no manual model registration.

Alternative: environment variables

For infrastructure-as-code setups, pass the connection at container start instead of clicking through the UI:

docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL="https://api.netraruntime.com/v1" \
  -e OPENAI_API_KEY="your-netra-api-key" \
  -v open-webui:/app/backend/data \
  ghcr.io/open-webui/open-webui:main

Step 2: chat

Pick your Netra model in the model selector and start chatting. Responses stream token by token, and every Open WebUI feature that layers on top of the model (document uploads and RAG, system prompts per model, usage controls for team members) works against your Netra endpoint unchanged.

Troubleshooting

• No models in the picker. The connection URL must end at /v1, and the container must be able to reach your endpoint. Verify from inside the container if unsure.
• Endpoint on the same host as Docker. Use host.docker.internal instead of localhost in the base URL; inside the container, localhost is the container itself.
• Connection verified but chats fail. Usually an expired or scoped-down API key. Generate a fresh key in the Netra dashboard and update the connection.

Frequently asked questions

Related

• Use Netra Runtime with any OpenAI-compatible tool
• How to use Netra Runtime with Dify
• What is token streaming?
• Hosted vs self-hosted inference