Skip to main content
POST
/
v1
/
responses
Image Analysis
curl --request POST \
  --url https://gptproto.com/v1/responses \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "<string>",
  "input": [
    {}
  ],
  "stream": true
}'
{
  "id": "resp-abc123",
  "object": "response",
  "created": 1699896916,
  "model": "gpt-41-nano",
  "output": "The image shows a wooden boardwalk path extending through a lush green grassland. The boardwalk appears to lead toward a distant tree line under a bright blue sky with some clouds. The grass on either side of the boardwalk is vibrant green, suggesting it might be spring or summer. The scene has a peaceful, natural atmosphere with good visibility and sunny weather conditions.",
  "usage": {
    "prompt_tokens": 1250,
    "completion_tokens": 89,
    "total_tokens": 1339
  }
}

​
Overview

This endpoint provides image-to-text functionality using vision-enabled models in response mode. provide image URLs to extract text content, describe scenes, or analyze visual information.

​
Authentication

This endpoint requires authentication using a Bearer token.
​
Authorization
string
default:"sk-***********"
required
Your API key in the format: sk-*****

​
Request Body

​
model
string
default:"gpt-41-nano"
required
The model to use for the request. Must be a vision-enabled model.
​
input
array
required
Array of message objects with role and content. Each message contains:
  • role: “user” or “assistant”
  • content: Array of content objects supporting the following types:
    • input_text: Text prompt with text field
    • input_image: Image input with image_url field, supports:
      • Base64 encoded images: data:image/jpeg;base64,{base64_string}
      • Supported formats: JPG, PNG
Example with base64 encoded image:
[
  {
    "role": "user",
    "content": [
      {
        "type": "input_text",
        "text": "What is in this image?"
      },
      {
        "type": "input_image",
        "image_url": "data:image/jpeg;base64,${base64Image}"
      }
    ]
  }
]
​
stream
boolean
default:false
Whether to stream the response

​
Request Example

curl --location 'https://gptproto.com/v1/responses' \
--header 'Authorization: sk-*****' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gpt-41-nano",
    "input": [
        {
            "role": "user",
            "content": [
                {
                    "type": "input_text",
                    "text": "What is in this image?"
                },
                {
                    "type": "input_image",
                    "image_url": "data:image/jpeg;base64,${base64Image}"
                }
            ]
        }
    ]
}'

​
Response

​
id
string
Unique identifier for the response
​
object
string
Object type, always “response”
​
created
integer
Unix timestamp of when the response was created
​
model
string
The model used for generating the response
​
output
string
The generated text output (the extracted text or image analysis)
​
usage
object
Token usage statistics
{
  "id": "resp-abc123",
  "object": "response",
  "created": 1699896916,
  "model": "gpt-41-nano",
  "output": "The image shows a wooden boardwalk path extending through a lush green grassland. The boardwalk appears to lead toward a distant tree line under a bright blue sky with some clouds. The grass on either side of the boardwalk is vibrant green, suggesting it might be spring or summer. The scene has a peaceful, natural atmosphere with good visibility and sunny weather conditions.",
  "usage": {
    "prompt_tokens": 1250,
    "completion_tokens": 89,
    "total_tokens": 1339
  }
}