> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# URL Context

> Compare two recipe pages by enabling Gemini's url_context to fetch page content.

> [!WARNING]
>
> This example's source docstring names the legacy `google-generativeai` package. Agno v3.0.4 uses the Google Gen AI SDK from `google-genai`. Use the generated install step below.

```python url_context.py theme={null}
"""Run `uv pip install google-generativeai` to install dependencies."""

from agno.agent import Agent
from agno.models.google import Gemini

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(
    model=Gemini(id="gemini-3.7-flash", url_context=True),
    markdown=True,
)

url1 = "https://www.foodnetwork.com/recipes/ina-garten/perfect-roast-chicken-recipe-1940592"
url2 = "https://www.allrecipes.com/recipe/83557/juicy-roasted-chicken/"

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    agent.print_response(
        f"Compare the ingredients and cooking times from the recipes at {url1} and {url2}"
    )
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno google-genai
```

**2. Export your Google API key**

```bash Mac/Linux theme={null}
export GOOGLE_API_KEY="your_google_api_key_here"
```

```bash Windows theme={null}
$Env:GOOGLE_API_KEY="your_google_api_key_here"
```

**3. Run the example**

Save the code above as `url_context.py`, then run:

```bash theme={null}
python url_context.py
```

Full source: [cookbook/90\_models/google/gemini/url\_context.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/google/gemini/url_context.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.