Google URL Context

Plugin ID: url_context

Description

The URL context tool lets you provide additional context to the models in the form of URLs. By including URLs in your request, the model will access the content from those pages to inform and enhance its response.

Cost Information

• Cost: 4 credits

• PixelML Cost: Based on the selected model pricing

Input Parameters

Parameter	Type	Required	Default	Description
model	string (dropdown)	Yes	"Gemini 2.5 Flash"	The Google Gemini model to use for processing the URL context. Options: Gemini 2.5 Pro, Gemini 2.5 Flash
prompt	string (long text)	Yes	-	The prompt that includes your question and the URL you want the model to analyze. Example: Summarize this document: https://ai.google.dev/gemini-api/docs/models
include_google_search	boolean	No	false	When enabled, the model can use Google Search to find relevant information online and combine it with the URL context for enhanced understanding.

Output

Field	Type	Description
result	string	The analyzed result from the URL context, containing the model's response based on the provided prompt and URL content.

How It Works

1. URL Processing: The action fetches content from the URLs included in your prompt

2. Context Analysis: The selected Gemini model analyzes the web page content

3. Enhanced Response: The model provides a response informed by both your prompt and the URL content

4. Search Integration: If Google Search is enabled, additional relevant information may be gathered and incorporated

Use Cases

• Document Summarization: Extract key points from web articles or documentation

• Content Analysis: Analyze specific web pages for insights or information

• Research Enhancement: Combine URL content with search capabilities for comprehensive research

• Web Content Q&A: Ask specific questions about content on web pages

Example Usage

Basic URL Analysis

Prompt: "What are the main features described on this page: https://example.com/product-features"
Model: Gemini 2.5 Flash
Include Google Search: false

Enhanced Research with Search

Prompt: "Compare the ingredients and cooking times from the recipes at https://www.foodnetwork.com/recipes/ina-garten/perfect-roast-chicken-recipe-1940592 and https://www.allrecipes.com/recipe/21151/simple-whole-roast-chicken/"
Model: Gemini 2.5 Pro
Include Google Search: true

Tips for Best Results

1. Be Specific: Include clear, specific questions in your prompt along with the URL

2. Choose the Right Model: Use Gemini 2.5 Pro for more complex analysis, Flash for faster responses

3. Enable Search When Needed: Use Google Search integration when you need additional context or comparison data

4. Provide Specific URLs: For the best results, provide direct URLs to the content you want the model to analyze. The model will only retrieve content from the URLs you provide, not any content from nested links.

5. Check for Accessibility: Verify that the URLs you provide don't lead to pages that require a login or are behind a paywall.

6. Use the Complete URL: Provide the full URL, including the protocol (e.g., https://www.google.com instead of just google.com).

Limitations

• URLs must be publicly accessible

• Request limit: The tool can process up to 20 URLs per request

• URL content size: The maximum size for content retrieved from a single URL is 34MB

• Pricing: Content retrieved from URLs counts as input tokens. Rate limit and pricing is based on the model used

• Content length may be limited by the model's context window

• Some websites may block automated access

• Processing time may vary depending on the complexity of the web content

Privacy & Compliance

• Only accesses publicly available web content from provided URLs

• Respects website robots.txt and access policies

• Complies with Google Gemini API terms of service

• No URL content is stored or cached after processing

• Users should ensure they have appropriate permissions to access and analyze the provided URLs

• Content analysis respects copyright and fair use guidelines

Error Handling

Common error scenarios:

• Invalid URL: Returns error for malformed or inaccessible URLs

• Content Too Large: Returns error if URL content exceeds 34MB limit

• Access Denied: Returns error for URLs requiring authentication or blocked by robots.txt

• Network Issues: Returns error if URLs are unreachable or timeout

• Model Limits: Returns error if content exceeds the selected model's context window

• Rate Limited: Temporary restriction if too many requests are made