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

# Image Input URL

> Point Claude at an image URL and search the web for more context.

Pass an image by URL with `Image(url=...)`. Agno downloads the image and sends it to Claude as base64.

## Code

```python image_input_url.py theme={null}
from agno.agent import Agent
from agno.media import Image
from agno.models.anthropic import Claude
from agno.tools.websearch import WebSearchTools

agent = Agent(
    model=Claude(id="claude-sonnet-4-20250514"),
    tools=[WebSearchTools()],
    markdown=True,
)

agent.print_response(
    "Tell me about this image and search the web for more information.",
    images=[
        Image(
            url="https://upload.wikimedia.org/wikipedia/commons/0/0c/GoldenGateBridge-001.jpg"
        ),
    ],
    stream=True,
)
```

## Usage

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

  <Step title="Set your API key">
    ```bash theme={null}
    export ANTHROPIC_API_KEY=xxx
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U anthropic agno ddgs
    ```
  </Step>

  <Step title="Run Agent">
    Save the code above as `image_input_url.py`, then run:

    ```bash theme={null}
    python image_input_url.py
    ```
  </Step>
</Steps>