Generate an image (OpenAI compatible)

POST

/v1/images/generations

OpenAI Images API compatible image generation.

Same request body, response body and billing as
POST /doubao/api/v3/images/generations; only the path and the accepted
response_format values differ.

Use this route when your client already speaks the OpenAI Images API.

Differences from the native route:

response_format: b64_json is supported here. The gateway downloads the
generated image and returns it inline.

multipart/form-data is accepted, so reference images can be uploaded as
files instead of URLs.

n must be 1; request several images with sequential_image_generation.

For parameter details, see the native route above.

请求参数

Authorization

JWT Bearer

在 Header 添加参数

Authorization

示例：

Authorization: ********************

Body 参数application/json必填

示例

Text to imageEdit one imageInline Base64 output

{
    "model": "doubao-seedream-5-0-flash-260915",
    "prompt": "A cyberpunk city at night, wet streets reflecting neon signs",
    "size": "2K"
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

cURL

Text to imageEdit one imageInline Base64 output

curl --location '/v1/images/generations' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "doubao-seedream-5-0-flash-260915",
    "prompt": "A cyberpunk city at night, wet streets reflecting neon signs",
    "size": "2K"
}'

返回响应

🟢200

application/json

Images generated.

Bodyapplication/json

示例

One image, URLOne edited imageInline Base64

{
    "data": [
        {
            "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/seedream/xxx.jpeg",
            "size": "2048x2048",
            "output_format": "jpeg"
        }
    ],
    "created": 1757469067,
    "usage": {
        "generated_images": 1,
        "output_tokens": 15908,
        "total_tokens": 15908
    }
}

🟠400BadRequest

🟠401Unauthorized

修改于 2026-10-28 04:38:45

Generate an image (Doubao native)

Edit an image (OpenAI compatible)