Hello Community,
I recently got my hands on ChatGPT-4o and was amazed by its capabilities. It accurately analyzed a stock image.
Since then, I have been wondering how it achieved this! If I want to obtain similar, mostly accurate image analysis results, are there any APIs for the gpt-4o model? Any insights on this topic would be very helpful.
1 Like
Go to openai api reference
/docs/api-reference/chat/create
Inside chat completion endpoint, check the messages and expand it, in User Message, show properties > see content(you need show properties several times…), you can find how to pass image input to your request
1 Like
The feature you’d want to use is called vision. There’s no special End Point for vision but you can use this via chat completion. Here’s an example:
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "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"
}
}
]
}
],
"max_tokens": 300
}'
for more info, check this part of Documentation
4 Likes