Send images, get answers
Vision
Send images to vision-enabled models as URLs or inline base64 data in the standard content array.
image_url → gpt-4o
# Cat Wearing a Top Hat- Seated on vintage chair- Book titled "Gentlecat's Guide"- Surrounded by indoor plants
01
URL or base64
Whatever you have, send it.
02
Multiple images
Compare several in one call.
03
Many models
Every vision model works.
04
Standard format
OpenAI content array.
Built for
Screenshot QA
Explain or debug a UI
Receipts
Pull totals from photos
Moderation
Describe what users upload
Ask about an image
request.json
1{2 "model": "gpt-4o",3 "messages": [4 {5 "role": "user",6 "content": [7 { "type": "text", "text": "What do you see?" },8 { "type": "image_url", "image_url": { "url": "https://example.com/photo.jpg" } }9 ]10 }11 ]12}