> ## 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.

# Together Image Agent

> Describe an image from a URL with a current Together vision model.

> [!WARNING]
>
> Together retired the source's `meta-llama/Llama-Vision-Free` serverless model. Select a current vision model from the [Together serverless catalog](https://docs.together.ai/docs/serverless/models) before running. See [Together vision inputs](https://docs.together.ai/docs/inference/vision/overview).

```python image_agent.py theme={null}
"""
Together Image Agent
====================

Cookbook example for `together/image_agent.py`.
"""

from agno.agent import Agent
from agno.media import Image
from agno.models.together import Together

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

agent = Agent(
    model=Together(id="meta-llama/Llama-Vision-Free"),
    markdown=True,
)

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

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

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

**1. Install dependencies**

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

**2. Export environment variables**

```bash Mac/Linux theme={null}
export TOGETHER_API_KEY="your_together_api_key_here"
export TOGETHER_VISION_MODEL_ID="your_current_together_vision_model_id_here"
```

```bash Windows theme={null}
$Env:TOGETHER_API_KEY="your_together_api_key_here"
$Env:TOGETHER_VISION_MODEL_ID="your_current_together_vision_model_id_here"
```

**3. Use the selected vision model**

Add `import os`, then replace `Together(id="meta-llama/Llama-Vision-Free")` with `Together(id=os.environ["TOGETHER_VISION_MODEL_ID"])` in the saved file.

**4. Run the example**

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

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

Full source: [cookbook/90\_models/together/image\_agent.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/together/image_agent.py)


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