URL context

Developing

POST

/v1beta/models/gemini-2.5-pro:generateContent

Official documentation: https://ai.google.dev/gemini-api/docs/url-context?hl=zh-cn

The URL context tool lets you provide more context to your model in the form of URLs. By adding URLs to the request, the model will access content from those pages (as long as it is not the URL type listed in the restrictions section), thereby informing and improving the quality of the answer.

The URL context tool is useful for the following tasks:

Extract data: Extract specific information like prices, names, or key findings from multiple URLs.
Compare documents: Analyze multiple reports, articles, or PDFs to find differences and track trends.
Synthesize and create content: Combine information from multiple source URLs to produce accurate summaries, blog posts, or reports.
Analyze code and documentation: Point to a GitHub repository or technical documentation to explain code, generate setup instructions, or answer questions.

Request

Query Params

Header Params

Body Params application/json

Example

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Interpreting this website https://www.youtube.com/watch?v=QCvF8mCPwdQ"
        }
      ]
    }
  ],
  "tools": [
    {
      "UrlContext": {}
    }
  ]
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --globoff '/v1beta/models/gemini-2.5-pro:generateContent?key={{YOUR_API_KEY}}' \
--header 'Authorization: Bearer  {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data '{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Interpreting this website https://www.youtube.com/watch?v=QCvF8mCPwdQ"
        }
      ]
    }
  ],
  "tools": [
    {
      "UrlContext": {}
    }
  ]
}'

Responses

🟢200OK

application/json

Bodyapplication/json

Example

{}

Modified at 2026-07-09 10:12:26

Video Understanding

Video understanding-url [native format]