Image Input

Requests with images, to multimodal models, are available via the /chat/completions API with a multi-part messagesparameter. The image_url can either be a URL or a base64-encoded image. You can send multiple images by adding more content entries in the same message.

URLs are preferred for large files since they avoid payload bloat. Use base64 encoding when working with local or private files.

Anannas supports both direct URLs and base64-encoded data for images:

URLs: More efficient for publicly accessible images as they don’t require local encoding
Base64: Required for local files or private images that aren’t publicly accessible

Using Image URLs

Here’s how to send an image via URL:

import requests
import json

url = "https://api.anannas.ai/v1/chat/completions"
headers = {
    "Authorization": f"Bearer {API_KEY_REF}",
    "Content-Type": "application/json"
}

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "What do you see in this image?"},
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://upload.wikimedia.org/wikipedia/commons/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
                    "detail": "high"
                }
            }
        ]
    }
]

payload = {"model": "{{MODEL}}", "messages": messages, "max_tokens": 300}

response = requests.post(url, headers=headers, json=payload)
print(response.json())

const response = await fetch('https://api.anannas.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${API_KEY_REF}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: '{{MODEL}}',
    max_tokens: 300,
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: "What do you see in this image?" },
          {
            type: 'image_url',
            image_url: {
              url: 'https://upload.wikimedia.org/wikipedia/commons/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg',
              detail: 'high',
            },
          },
        ],
      },
    ],
  }),
});

const data = await response.json();
console.log(data);

Using Base64 Encoded Images (OpenAI only)

For OpenAI models, you can send local images as base64:

import requests, base64

def encode_image_to_base64(image_path):
    with open(image_path, "rb") as f:
        return base64.b64encode(f.read()).decode("utf-8")

url = "https://api.anannas.ai/v1/chat/completions"
headers = {
    "Authorization": f"Bearer {API_KEY_REF}",
    "Content-Type": "application/json"
}

base64_image = encode_image_to_base64("path/to/image.jpg")
data_url = f"data:image/jpeg;base64,{base64_image}"

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "What do you see in this image?"},
            {
                "type": "image_url",
                "image_url": {"url": data_url, "detail": "high"}
            }
        ]
    }
]

payload = {"model": "{{MODEL}}", "messages": messages, "max_tokens": 300}

response = requests.post(url, headers=headers, json=payload)
print(response.json())

import fs from 'fs/promises';

async function encodeImageToBase64(path: string): Promise<string> {
  const buffer = await fs.readFile(path);
  return `data:image/jpeg;base64,${buffer.toString('base64')}`;
}

const imageData = await encodeImageToBase64('path/to/image.jpg');

const response = await fetch('https://api.anannas.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${API_KEY_REF}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: '{{MODEL}}',
    max_tokens: 300,
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: "What do you see in this image?" },
          {
            type: 'image_url',
            image_url: { url: imageData, detail: 'high' },
          },
        ],
      },
    ],
  }),
});

const data = await response.json();
console.log(data);

Supported image types:

Check Vision Model Support

For models that support image inputs and their capabilities, visit anannas.ai/models.

image/png
image/jpeg
image/webp
image/gif

Was this page helpful?

Getting Started

Features

API

Models

Use Cases

Community

Using Image URLs

Using Base64 Encoded Images (OpenAI only)

Supported image types:

Check Vision Model Support

​Using Image URLs

​Using Base64 Encoded Images (OpenAI only)

​Supported image types:

Check Vision Model Support

Using Image URLs

Using Base64 Encoded Images (OpenAI only)

Supported image types: