> ## Documentation Index
> Fetch the complete documentation index at: https://docs.duiapi.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# First test

> Send your first request

After creating an API key, send a simple request to test whether the API is available.

## Endpoint

```http theme={null}
POST https://www.duiapi.com/v1/messages
```

## Authentication and model selection

Send `x-api-key` in the request headers and specify the model you want to use.

```http theme={null}
<API_KEY> Replace with your API key, such as sk-xxxxxx
<MODEL> Replace with the model you use, such as qwen3.7-max
```

## Request examples

<CodeGroup>
  ```bash cURL theme={null}
  curl -sS 'https://www.duiapi.com/v1/messages' \
    -X POST \
    -H 'content-type: application/json' \
    -H 'x-api-key: <API_KEY>' \
    -H 'anthropic-version: 2023-06-01' \
    -H 'anthropic-dangerous-direct-browser-access: true' \
    --data-binary '{
      "model": "<MODEL>",
      "max_tokens": 64,
      "messages": [
        {
          "role": "user",
          "content": "just say hello world"
        }
      ]
    }'
  ```

  ```javascript Node.js theme={null}
  const apiKey = "<API_KEY>";
  const model = "<MODEL>";

  const response = await fetch("https://www.duiapi.com/v1/messages", {
    method: "POST",
    headers: {
      "content-type": "application/json",
      "x-api-key": apiKey,
      "anthropic-version": "2023-06-01",
      "anthropic-dangerous-direct-browser-access": "true",
    },
    body: JSON.stringify({
      model,
      max_tokens: 64,
      messages: [{ role: "user", content: "just say hello world" }],
    }),
  });

  const data = await response.json();
  console.log(data);
  ```

  ```python Python theme={null}
  import requests

  api_key = "<API_KEY>"
  model = "<MODEL>"

  response = requests.post(
      "https://www.duiapi.com/v1/messages",
      headers={
          "content-type": "application/json",
          "x-api-key": api_key,
          "anthropic-version": "2023-06-01",
          "anthropic-dangerous-direct-browser-access": "true",
      },
      json={
          "model": model,
          "max_tokens": 64,
          "messages": [{"role": "user", "content": "just say hello world"}],
      },
      timeout=30,
  )

  print(response.json())
  ```
</CodeGroup>

## Common errors

| HTTP status                   | Cause                                                           | How to fix                                            |
| ----------------------------- | --------------------------------------------------------------- | ----------------------------------------------------- |
| `401`                         | The key is invalid, disabled, or expired                        | Check the `x-api-key` header or create a new token    |
| `400 insufficient_user_quota` | Account balance or key quota is insufficient                    | Recharge your account                                 |
| `400 model_not_found`         | The model does not exist, or is outside this key or group scope | Confirm the model ID and group in Model Marketplace   |
| `429`                         | Rate limit triggered                                            | Retry with exponential backoff, or reduce concurrency |

The `type` and `code` fields in error responses contain more specific error categories. Branch on these fields in your client instead of parsing only the `message` text.

## Next steps

After one request works, continue exploring:

* [Connect models through Agent tools](/en/agent-configuration/claude-code/model-support)
* [Connect models through API](/en/api-reference/introduction)