创建 gpt-image-2

POST

/v1/images/generations

给定一个提示，该模型将返回一个或多个预测的完成，并且还可以返回每个位置的替代标记的概率。

为提供的提示和参数创建完成

官方文档：https://platform.openai.com/docs/api-reference/images/create

Request

Header Params

Body Params application/json

Example

{
    "model": "gpt-image-2",
    "prompt": "A childrens book drawing of a veterinarian using a stethoscope to listen to the heartbeat of a baby otter.",
    "n": 1,
    "size": "1024x1024",
    "quality": "low",
    "format": "jpeg"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/images/generations' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gpt-image-2",
    "prompt": "A childrens book drawing of a veterinarian using a stethoscope to listen to the heartbeat of a baby otter.",
    "n": 1,
    "size": "1024x1024",
    "quality": "low",
    "format": "jpeg"
}'

Responses

🟢200OK

application/json

Bodyapplication/json

Example

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\nHello there, how may I assist you today?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}

Modified at 2026-05-02 07:40:16

编辑 gpt-image-2

创建 gpt-image-2-all