同步生成 GPT Image 图片

curl --request POST \
  --url https://api.yingtu.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2-web",
  "prompt": "浅色桌面上的蓝色陶瓷茶壶，不要文字"
}
'

{
  "created": 1788307200,
  "data": [
    {
      "b64_json": "iVBORw0KGgo="
    }
  ],
  "usage": {
    "input_tokens": 24,
    "output_tokens": 1756,
    "total_tokens": 1780,
    "input_tokens_details": {
      "text_tokens": 24,
      "image_tokens": 0
    },
    "output_tokens_details": {
      "text_tokens": 0,
      "image_tokens": 1756
    }
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "Insufficient balance for this request",
    "type": "new_api_error",
    "param": "",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "insufficient_user_quota"
  }
}

POST

images

generations

curl --request POST \
  --url https://api.yingtu.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2-web",
  "prompt": "浅色桌面上的蓝色陶瓷茶壶，不要文字"
}
'

{
  "created": 1788307200,
  "data": [
    {
      "b64_json": "iVBORw0KGgo="
    }
  ],
  "usage": {
    "input_tokens": 24,
    "output_tokens": 1756,
    "total_tokens": 1780,
    "input_tokens_details": {
      "text_tokens": 24,
      "image_tokens": 0
    },
    "output_tokens_details": {
      "text_tokens": 0,
      "image_tokens": 1756
    }
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "Insufficient balance for this request",
    "type": "new_api_error",
    "param": "",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "insufficient_user_quota"
  }
}

调用方可以保持连接直到图片完成时使用该接口。model 选择 Web 或 VIP；两个逆向接口都会转发 quality，实际效果取决于所选上游。

在线测试会产生真实费用。发送前确认模型、尺寸和 quality，并且不要分享包含密钥的 cURL。

需要快速获得 task_id 时，改用统一异步图片任务，并设置 action=generate。

授权

Authorization

string

header

必填

YingTu API Key。

请求体

application/json

model

enum<string>

必填

可用选项:

gpt-image-2-web,

gpt-image-2-vip

示例:

"gpt-image-2-web"

prompt

string

必填

Minimum string length: 1

示例:

"浅色桌面上的蓝色陶瓷茶壶，不要文字"

size

enum<string>

当前公开支持三档尺寸。请明确传入 size 以获得可预测的像素尺寸；4K 横图使用 3840x2160。

可用选项:

1024x1024,

2048x2048,

3840x2160

示例:

"1024x1024"

quality

enum<string>

两个 GPT Image 接口都会转发该值；实际效果由所选上游决定。

可用选项:

low,

medium,

high,

auto

示例:

"low"

enum<integer>

默认值:1

当前文档子集返回一张图片。

可用选项:

1

响应

完整 GPT Image 响应

created

integer<int64>

必填

Unix 秒级时间戳。

data

object[]

必填

Required array length: 1 element

Show child attributes

size

string

Output size when returned by the selected GPT Image route.

quality

string

Quality value reported by the selected GPT Image route.

usage

object

Show child attributes

最后修改于 2026年9月3日