# Connect your software

Source: [https://docs.aventail.co.uk/docs/getting-started/run-first-interface](https://docs.aventail.co.uk/docs/getting-started/run-first-interface)

Keep your model serving and run the first test **on the same machine as Link**.

### Send a local request

Use the exact model ID and your actual serving port.

1.  **Find the endpoint**
    
    Open Serving → API Usage in Control. On the Link machine, the walkthrough uses http://127.0.0.1:8100/v1.
    
    [Screenshot: Local API Usage — close-up from Model Serving in Control.](https://docs.aventail.co.uk/img/guides/context/serving.png)
    
2.  **Ask the model**
    
    Use the copyable commands in the written steps. A successful test returns non-empty assistant content.
    
    -   GET /v1/models: Copy an exact model ID
    -   POST /v1/chat/completions: Send the prompt with that ID
    -   Inspect choices\[0\].message.content: Check the complete response

**Read the API steps and copy commands**

Send a request to the model running through Link, then use the same endpoint in your application.

## Before you start

Complete [setup and serving](https://docs.aventail.co.uk/docs/getting-started/quickstartguide#deploy). Keep Link running and open Terminal **on the same Mac**. Aventail setup serves on port `8100`. If you configured another endpoint, use its actual port.

*Tested: Aventail Link 2.0.0 · Llama 3.2 3B Instruct Q4\_K\_M · Apple Silicon · 2 October 2026.*

## 1\. Find your model ID

Replace `8100` if you chose a different port:

```bash
curl --fail-with-body --silent --show-error \
  http://127.0.0.1:8100/v1/models
```

Copy an `id` from the returned `data` array. Use that exact value, including spaces and punctuation, in the next request.

Local connection

Use `127.0.0.1` for requests on this Mac, not the bind address `0.0.0.0`. Serving can listen on all interfaces; review network exposure before connecting other machines.

## 2\. Send a request

Save this as `request.json`, replacing the model ID with yours:

```json
{
  "model": "Llama-3.2-3B-Instruct-Q4_K_M",
  "messages": [{"role": "user", "content": "Reply with exactly: Aventail is ready."}],
  "max_tokens": 32,
  "temperature": 0,
  "stream": false
}
```

Run:

```bash
curl --fail-with-body --silent --show-error --max-time 180 \
  -H 'Content-Type: application/json' \
  --data-binary @request.json \
  http://127.0.0.1:8100/v1/chat/completions
```

## 3\. Check the response

A successful test needs a successful HTTP response **and non-empty `choices[0].message.content`**. The recorded response included:

```json
{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Aventail is ready."
      }
    }
  ]
}
```

The wording can vary. The response may report the model file path instead of the request's alias.

## Connect an application

Use `http://127.0.0.1:8100/v1` as the base URL for an OpenAI-compatible client on this Mac, with the model ID returned above. Browser clients also need an allowed origin; see the [Link integration reference](https://docs.aventail.co.uk/docs/integration/your-own-software#cors).

For app-specific setup, see [Continue in VS Code](https://docs.aventail.co.uk/docs/integration/vscode), [Open WebUI](https://docs.aventail.co.uk/docs/integration/openwebui), [Obsidian](https://docs.aventail.co.uk/docs/integration/obsidian), or [OpenClaw](https://docs.aventail.co.uk/docs/integration/openclaw). You can also [chat in Workspace](https://docs.aventail.co.uk/docs/workspace/getting-started).

## If the request fails

| Symptom | Next action |
| --- | --- |
| Connection refused | Confirm Link is running, serving started, and the port matches Control. |
| Model-name/router error | Call `/v1/models` again and copy an exact `id`. |
| HTTP success but empty content | Inspect `finish_reason`. If it is `length`, increase `max_tokens` for the model and task. |
| First request is slow | Allow time for engine/model startup. Retain any error text rather than repeatedly redeploying the model. |

To stop serving, open **Serving** in Control, expand the device and turn off the model's switch. The model stays installed.