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

# Vision

> Send images to multimodal models for analysis, description, and reasoning.

## Overview

Vision-capable models can analyze images alongside text. Pass image URLs or base64-encoded images in the `content` field of your messages.

## Supported Models

| Model                        | Provider    | Notes                             |
| ---------------------------- | ----------- | --------------------------------- |
| `gpt-4o`                     | OpenAI      | Best overall vision               |
| `gpt-4o-mini`                | OpenAI      | Fast and affordable               |
| `claude-3-5-sonnet-20241022` | Anthropic   | Excellent document understanding  |
| `gemini-2.0-flash`           | Google      | Fast, 1M context                  |
| `gemini-2.5-pro`             | Google      | Best for complex visual reasoning |
| `llava-1.6`                  | Open Source | Open-weight vision model          |

## Using Image URLs

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-samurai-YOUR_KEY",
      base_url="https://api.samuraiapi.in/v1"
  )

  response = client.chat.completions.create(
      model="gpt-4o",
      messages=[
          {
              "role": "user",
              "content": [
                  {
                      "type": "image_url",
                      "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg"}
                  },
                  {
                      "type": "text",
                      "text": "What is in this image? Describe it in detail."
                  }
              ]
          }
      ]
  )

  print(response.choices[0].message.content)
  ```

  ```javascript Node.js theme={null}
  const response = await client.chat.completions.create({
    model: 'gpt-4o',
    messages: [
      {
        role: 'user',
        content: [
          {
            type: 'image_url',
            image_url: { url: 'https://example.com/image.jpg' }
          },
          {
            type: 'text',
            text: 'What is in this image?'
          }
        ]
      }
    ]
  });
  ```
</CodeGroup>

## Using Base64 Images

```python theme={null}
import base64

with open("screenshot.png", "rb") as f:
    image_data = base64.b64encode(f.read()).decode("utf-8")

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": f"data:image/png;base64,{image_data}"
                    }
                },
                {"type": "text", "text": "Extract all text from this screenshot."}
            ]
        }
    ]
)
```

## Multiple Images

```python theme={null}
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "image_url", "image_url": {"url": "https://example.com/before.jpg"}},
                {"type": "image_url", "image_url": {"url": "https://example.com/after.jpg"}},
                {"type": "text", "text": "What changed between these two images?"}
            ]
        }
    ]
)
```

## Supported Formats

PNG, JPEG, GIF, WebP — max 20MB per image.