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

# Web fetch server tool

> Fetch text from public URLs during a model response with the orq:web_fetch server tool.

The `orq:web_fetch` tool retrieves text from a URL chosen by the model. The **AI Gateway** checks the URL before fetching it and returns the extracted content to the model.

## Quick start

The examples use the client configuration from the [Server tools overview](/docs/ai-gateway/features/server-tools).

<CodeGroup>
  ```bash cURL theme={"theme":{"light":"github-light","dark":"github-dark"}}
  curl -X POST https://api.orq.ai/v3/router/chat/completions \
    -H "Authorization: Bearer $ORQ_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "openai/gpt-5.4-mini",
      "messages": [
        {
          "role": "user",
          "content": "Summarize https://docs.example.com/release-notes"
        }
      ],
      "tools": [
        {
          "type": "orq:web_fetch",
          "max_content_tokens": 4000,
          "allowed_domains": ["docs.example.com"]
        }
      ]
    }'
  ```

  ```typescript TypeScript theme={"theme":{"light":"github-light","dark":"github-dark"}}
  const response = await client.chat.completions.create({
    model: 'openai/gpt-5.4-mini',
    messages: [
      {
        role: 'user',
        content: 'Summarize https://docs.example.com/release-notes',
      },
    ],
    tools: [
      {
        type: 'orq:web_fetch',
        max_content_tokens: 4000,
        allowed_domains: ['docs.example.com'],
      },
    ] as any,
  });

  console.log(response.choices[0].message.content);
  ```

  ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
  response = client.chat.completions.create(
      model="openai/gpt-5.4-mini",
      messages=[
          {
              "role": "user",
              "content": "Summarize https://docs.example.com/release-notes",
          }
      ],
      tools=[
          {
              "type": "orq:web_fetch",
              "max_content_tokens": 4000,
              "allowed_domains": ["docs.example.com"],
          }
      ],
  )

  print(response.choices[0].message.content)
  ```
</CodeGroup>

## Configuration

| Parameter            | Type      | Required | Default                | Description                                                                               |
| -------------------- | --------- | -------- | ---------------------- | ----------------------------------------------------------------------------------------- |
| `type`               | string    | Yes      |                        | Must be `orq:web_fetch`.                                                                  |
| `engine`             | string    | No       | `auto`                 | Fetch engine. Accepted values are `auto` and `jina`.                                      |
| `max_uses`           | integer   | No       | Unlimited              | Maximum fetches during the request. Set `0` or omit the field for no tool-specific limit. |
| `max_content_tokens` | integer   | No       | No tool-specific limit | Truncate extracted content to approximately this many tokens. Minimum: 1.                 |
| `allowed_domains`    | string\[] | No       | All domains            | Only fetch URLs from the listed domains.                                                  |
| `blocked_domains`    | string\[] | No       | None                   | Reject URLs from the listed domains.                                                      |

## URL restrictions

The tool accepts public `http` and `https` URLs. It rejects loopback, link-local, private, and unspecified IP addresses. Domain rules are checked before the fetch runs.

When a URL is rejected, the model receives the reason and can choose another URL. Rejected URLs do not use a `max_uses` slot.

## Usage

Fetches that pass URL validation and the usage limit appear at `usage.server_tool_use.web_fetch_requests`. There is no separate server-tool charge for web fetch in this release.

Use [Web search](/docs/ai-gateway/features/server-tools/web-search) when the URL is not known in advance.