AI Model InterfaceImagesGPT Image 2
GPT Image 2 Image Generation (OpenAI Chat Format)
Use the OpenAI Chat Completions compatible format /v1/chat/completions to call GPT Image 2 for image generation. Simply pass model, messages, and stream, with extra_body not required by default. Images are typically returned in Markdown data URI format to choices[].message.content.
Authorization
Bearer
AuthorizationBearer <token>
In: header
Request Body
application/json
model*string
模型名称。支持 gpt-image-2、gpt-image-2-vip、gpt-image-2-1k、gpt-image-2-2k、gpt-image-2-4k。
Value in
"gpt-image-2" | "gpt-image-2-vip" | "gpt-image-2-1k" | "gpt-image-2-2k" | "gpt-image-2-4k"messages*
OpenAI 聊天消息。使用生图提示词，不要写成图像理解问题。
stream?boolean
是否流式返回。
Response Body
application/json
curl -X POST "https://nodekey.xinghanyun.cn/v1/chat/completions" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-image-2", "messages": [ { "role": "user", "content": "画一只戴着贝雷帽的小猫，白色背景，插画风格" } ], "stream": false }'{
"id": "string",
"object": "string",
"created": 0,
"model": "string",
"choices": [
{
"index": 0,
"message": {
"role": "string",
"content": "string"
},
"finish_reason": "string"
}
],
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0
}
}Last updated on