Image understanding (vision)

Supported models

All models above support vision input. Refer to the capability labels in the Model Catalog (Models in the console).

Input methods

In messages, use content as an array of content parts. Use text parts for text and image_url parts for images. Images can be supplied in two ways:

• Image URL: Provide a publicly accessible image address when the image is already online.
• Base64 encoding: Encode a local image as a data URL in the form data:image/jpeg;base64,..., suitable for local files or private-network images.

Code examples

Python (image URL)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.yomiapi.com/v1"
)
response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What is 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"}}
        ]
    }],
    max_tokens=300
)
print(response.choices[0].message.content)

Python (local image as Base64)

import base64
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.yomiapi.com/v1"
)
with open("photo.jpg", "rb") as f:
    b64 = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Recognize the text in the image and return plain text"},
            {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{b64}"}}
        ]
    }]
)
print(response.choices[0].message.content)

cURL

curl https://api.yomiapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Describe the contents of this image"},
        {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
      ]
    }]
  }'

Recommendations

• Image quality: Clear images with a distinct subject are easier to recognize. Use high-resolution originals for OCR when possible.
• Multiple images: A message can contain multiple image_url parts to compare or relate images.
• Ask specifically: State precise requirements, such as "Extract the table as Markdown" or "Output only the phone number in the image", for more controllable results than a broad request to describe the image.