Documentation

Python Vision

Multimodal chat models accept images as an image_url content part on POST /v1/chat/completions — no separate endpoint.

Start

Help

Python Setup

Node.js Setup

PHP Setup

API Reference

main.py

response = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}},
            ],
        }
    ],
)
print(response.choices[0].message.content)

For local files, pass a data URL instead of a public one: {"image_url": {"url": "data:image/jpeg;base64,<...>"}}. Only models with vision support upstream will use the image — check the model's details before relying on it.