gpt-image-2
Submit an async gpt-image-2 image generation task. Returns a task_id to poll via the status endpoint.
Authorization
BearerAuth
AuthorizationBearer <token>
使用 Bearer Token 认证。
格式: Authorization: Bearer sk-xxxxxx
In: header
Request Body
application/json
model*string
模型名。固定为 gpt-image-2
input*object
prompt*string
图片描述（必填，非空）
size?string
比例 1:1 / 16:9 / 9:16 / auto，或像素形态 1024x1024（服务端会化简为比例）
image?string
单张参考图 URL（与 images 二选一或合并使用）
images?array<string>
多张参考图 URL；最多 16 张，超出会被截断
Items
items <= 16metadata?object
模型专属参数。下列字段会被透传到上游。
quality?string
图片质量。gpt-image-2 不支持 auto，传入会被上游 400 拒绝
Value in
"low" | "medium" | "high"resolution?string
输出分辨率
Value in
"1K" | "2K" | "4K"n?integer
生成数量（gpt-image-2 专属）
Range
1 <= value <= 4mask_url?string
编辑模式蒙版 URL（gpt-image-2 编辑用）
model_params?object
完全透传到上游的额外字段
[key: string]?any
[key: string]?never
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
curl -X POST "https://loading/api/generate/submit" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-image-2", "input": { "prompt": "A red panda riding a skateboard, cinematic lighting" } }'{
"code": 200,
"data": {
"task_id": "task_0VDknz6qRwvH5Y5aDAt6mN8pRShzLb6X",
"status": "not_started",
"created_time": "2026-06-18T09:21:26",
"error_message": null
}
}{
"code": 400,
"error": {
"message": "input.prompt is required",
"type": "invalid_request_error"
}
}{
"code": 400,
"error": {
"message": "string",
"type": "invalid_request_error"
}
}{
"code": 400,
"error": {
"message": "string",
"type": "invalid_request_error"
}
}{
"code": 400,
"error": {
"message": "string",
"type": "invalid_request_error"
}
}{
"code": 400,
"error": {
"message": "string",
"type": "invalid_request_error"
}
}How is this guide?
Last updated on