---
title: Image Inputs
description: Send images to vision models through the Agnic AI Gateway
---

# Image Inputs

Send images to multimodal models for analysis, description, OCR, and more. Agnic supports multiple image formats and both URL-based and base64-encoded images.

## Overview

Image requests are available via the `/v1/chat/completions` API with a multi-part `messages` parameter. The `image_url` can either be a URL or a base64-encoded image.

<Callout type="tip">
  Multiple images can be sent in separate content array entries. We recommend sending the text prompt first, then the images for best results.
</Callout>

---

## Using Image URLs

For publicly accessible images, send the URL directly:

### Python

```python
from openai import OpenAI

client = OpenAI(
    api_key="agnic_tok_YOUR_TOKEN",
    base_url="https://api.agnic.ai/v1"
)

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "What's in this image?"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
                    }
                }
            ]
        }
    ]
)

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

### JavaScript

```javascript
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'agnic_tok_YOUR_TOKEN',
  baseURL: 'https://api.agnic.ai/v1'
});

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [
    {
      role: 'user',
      content: [
        {
          type: 'text',
          text: "What's in this image?"
        },
        {
          type: 'image_url',
          image_url: {
            url: 'https://example.com/image.jpg'
          }
        }
      ]
    }
  ]
});

console.log(response.choices[0].message.content);
```

### cURL

```bash
curl https://api.agnic.ai/v1/chat/completions \
  -H "Authorization: Bearer agnic_tok_YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "What is in this image?"},
          {
            "type": "image_url",
            "image_url": {
              "url": "https://example.com/image.jpg"
            }
          }
        ]
      }
    ]
  }'
```

---

## Using Base64 Encoded Images

For locally stored images, use base64 encoding:

### Python

```python
from openai import OpenAI
import base64

def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode('utf-8')

client = OpenAI(
    api_key="agnic_tok_YOUR_TOKEN",
    base_url="https://api.agnic.ai/v1"
)

# Read and encode the image
image_path = "path/to/your/image.jpg"
base64_image = encode_image(image_path)
data_url = f"data:image/jpeg;base64,{base64_image}"

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "What's in this image?"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": data_url
                    }
                }
            ]
        }
    ]
)

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

### JavaScript

```javascript
import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'agnic_tok_YOUR_TOKEN',
  baseURL: 'https://api.agnic.ai/v1'
});

// Read and encode the image
const imagePath = 'path/to/your/image.jpg';
const imageBuffer = fs.readFileSync(imagePath);
const base64Image = imageBuffer.toString('base64');
const dataUrl = `data:image/jpeg;base64,${base64Image}`;

const response = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [
    {
      role: 'user',
      content: [
        {
          type: 'text',
          text: "What's in this image?"
        },
        {
          type: 'image_url',
          image_url: {
            url: dataUrl
          }
        }
      ]
    }
  ]
});

console.log(response.choices[0].message.content);
```

---

## Supported Image Formats

| Format | MIME Type | Extension |
|--------|-----------|-----------|
| PNG | `image/png` | `.png` |
| JPEG | `image/jpeg` | `.jpg`, `.jpeg` |
| WebP | `image/webp` | `.webp` |
| GIF | `image/gif` | `.gif` |

---

## Multiple Images

Send multiple images in a single request:

```python
response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Compare these two images"
                },
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/image1.jpg"}
                },
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/image2.jpg"}
                }
            ]
        }
    ]
)
```

---

## Compatible Models

Models with vision capabilities include:

| Provider | Models |
|----------|--------|
| OpenAI | `openai/gpt-4o`, `openai/gpt-4o-mini`, `openai/gpt-4-turbo` |
| Anthropic | `anthropic/claude-3.5-sonnet`, `anthropic/claude-3-opus`, `anthropic/claude-3-haiku` |
| Google | `google/gemini-2.0-flash`, `google/gemini-1.5-pro`, `google/gemini-1.5-flash` |

Check the model's `architecture.input_modalities` for `"image"` support.

---

## Best Practices

1. **Use URLs for public images** - More efficient than base64 encoding
2. **Compress large images** - Reduce payload size without losing quality
3. **Send text first** - Place your prompt before the images
4. **Check model limits** - Different models have different image count limits

<Cards>
  <Card title="Image Generation" href="/docs/ai-gateway/multimodal/image-generation" />
  <Card title="PDF Processing" href="/docs/ai-gateway/multimodal/pdfs" />
</Cards>