Generate a GPT Image image - YingTu API Docs

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": "A blue ceramic teapot on a pale table, no text"
}
'

{
  "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": "A blue ceramic teapot on a pale table, no text"
}
'

{
  "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"
  }
}

Use this JSON operation when the caller can keep one connection open until the image is complete. Set model to gpt-image-2-web or gpt-image-2-vip; consult the selected model’s Parameters page before adding quality.

Try it sends a real billable request. Confirm model, size, and quality, use a development key, and do not share generated cURL that contains the key.

Task workers that need an early task ID should use the unified image-task endpoint with action=generate.

Authorizations

Authorization

string

header

required

YingTu API key.

Body

application/json

model

enum<string>

required

Available options:

gpt-image-2-web,

gpt-image-2-vip

Example:

"gpt-image-2-web"

prompt

string

required

Minimum string length: 1

Example:

"A blue ceramic teapot on a pale table, no text"

size

enum<string>

Current public presets. Set size explicitly for predictable dimensions; the 4K landscape value is 3840x2160.

Available options:

1024x1024,

2048x2048,

3840x2160

Example:

"1024x1024"

quality

enum<string>

Forwarded for both GPT Image routes. The selected upstream determines how the requested value affects the result.

Available options:

low,

medium,

high,

auto

Example:

"low"

enum<integer>

default:1

The documented subset returns one image.

Available options:

1

Response

Complete GPT Image response

created

integer<int64>

required

Unix timestamp in seconds.

data

object[]

required

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

Last modified on September 3, 2026