创建 gpt-image-2

用户版环境

https://api.nicerouter.com

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

请求参数

Header 参数

Body 参数application/json

示例

{
    "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"
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://api.nicerouter.com/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"
}'

返回响应

🟢200OK

application/json

Bodyapplication/json

示例

{
    "created": 1776911231,
    "background": "opaque",
    "data": [
        {
            "b64_json": "XXXX"
        }
    ],
    "output_format": "png",
    "quality": "low",
    "size": "1024x1024",
    "usage": {
        "input_tokens": 29,
        "input_tokens_details": {
            "image_tokens": 0,
            "text_tokens": 29
        },
        "output_tokens": 208,
        "total_tokens": 237
    }
}

修改于 2026-04-23 08:34:27

编辑 gpt-image-2

创建 Image