URL context

The URL context tool lets you provide Gemini with URLs as additional context for your prompt. The model retrieves content from the URLs and uses that content to inform and shape its response.

This tool is useful for tasks such as the following:

  • Extracting key data points or talking points from articles.
  • Comparing information across multiple links.
  • Synthesizing data from several sources.
  • Answering questions based on the content of a specific page or pages.
  • Analyzing content for specific purposes, like writing a job description or creating test questions.

This page shows you how to use the URL context tool with the Gemini API in Vertex AI.

Supported models

The following models support URL context:

Use URL context

To use the URL context tool, provide one or more URLs in your prompt for the model to analyze.

For example:

Summarize this document: YOUR_URLs

Extract the key features from the product description on this page: YOUR_URLs

Python

from google import genai
from google.genai.types import Tool, GenerateContentConfig, HttpOptions, UrlContext

client = genai.Client(http_options=HttpOptions(api_version="v1"))
model_id = "gemini-2.5-flash"

url_context_tool = Tool(
    url_context = UrlContext
)

response = client.models.generate_content(
    model=model_id,
    contents="Compare recipes from YOUR_URL1 and YOUR_URL2",
    config=GenerateContentConfig(
        tools=[url_context_tool],
        response_modalities=["TEXT"],
    )
)

for each in response.candidates[0].content.parts:
    print(each.text)
# get URLs retrieved for context
print(response.candidates[0].url_context_metadata)

Javascript

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  vertexai: true,
  project: process.env.GOOGLE_CLOUD_PROJECT,
  location: process.env.GOOGLE_CLOUD_LOCATION,
  apiVersion: 'v1',
});

async function main() {
  const response = await ai.models.generateContent({
    model: "gemini-2.5-flash",
    contents: [
        "Compare recipes from YOUR_URL1 and YOUR_URL2",
    ],
    config: {
      tools: [{urlContext: {}}],
    },
  });
  console.log(response.text);
  // To get URLs retrieved for context
  console.log(response.candidates[0].urlContextMetadata)
}

await main();

REST

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://aiplatform.googleapis.com/v1beta1/projects/GOOGLE_CLOUD_PROJECT/locations/global/publishers/google/models/gemini-2.5-flash:generateContent
  -d '{
      "contents": [
          {
              "parts": [
                  {"text": "Compare recipes from YOUR_URL1 and YOUR_URL2"}
              ]
          }
      ],
      "tools": [
          {
              "url_context": {}
          }
      ]
  }' > result.json

cat result.json

Contextual response

The model's response is based on the content it retrieves from the URLs. If the model retrieves content from URLs, the response includes url_context_metadata. The following example shows a response that includes this metadata. For brevity, parts of the response are omitted.

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "... \n"
          }
        ],
        "role": "model"
      },
      ...
      "url_context_metadata":
      {
          "url_metadata":
          [
            {
              "retrieved_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/code-execution",
              "url_retrieval_status": <UrlRetrievalStatus.URL_RETRIEVAL_STATUS_SUCCESS: "URL_RETRIEVAL_STATUS_SUCCESS">
            },
            {
              "retrieved_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/grounding/grounding-with-google-search",
              "url_retrieval_status": <UrlRetrievalStatus.URL_RETRIEVAL_STATUS_SUCCESS: "URL_RETRIEVAL_STATUS_SUCCESS">
            },
          ]
        }
    }
}

Limitations

  • The tool consumes up to 20 URLs per request for analysis.
  • The tool does not fetch live versions of web pages, so there might be issues with freshness or out-of-date information.
  • For best results during the experimental phase, use the tool on standard web pages rather than on multimedia content such as YouTube videos.