Web fetch server tool - Orq.ai Documentation

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.

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"]
      }
    ]
  }'

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);

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)

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 when the URL is not known in advance.

⌘I