生成图片(chat)

POST

/v1/chat/completions

根据提示词生成图片。
需要模型支持生图能力，比如：gpt-4o-image，gemini-2.5-flash-image-preview，gemini-3-pro-image-preview (nano-banana2)
非openai的模型，比如 jimeng，banana，可以在提示词通过横屏，竖屏来指定图片比例，但是无法指定具体的size

请求参数

Header 参数

Body 参数application/json

示例

{
   "model": "gpt-4o-image",
   "stream": false,
   "messages": [
      {
         "role": "user",
         "content": "画只猫"
      }
   ]
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.wenwen-ai.com/v1/chat/completions' \
--header 'Authorization: Bearer {YOUR_API_KEY}' \
--header 'Content-Type: application/json' \
--data-raw '{
   "model": "gpt-4o-image",
   "stream": false,
   "messages": [
      {
         "role": "user",
         "content": "画只猫"
      }
   ]
}'

返回响应

🟢200成功

application/json

Body

示例

{
    "id": "chatcmpl-2ae838b1-6281-47fd-9a49-a1dc7bfd0d97",
    "object": "chat.completion",
    "created": 1749370100,
    "model": "sora_image",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "![图片](https://midjourney-plus.oss-us-west-1.aliyuncs.com/sora/75d509d1-4c64-4299-8286-29c1f11db701.png)\n\n"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 0,
        "completion_tokens": 0,
        "total_tokens": 0
    }
}

修改于 2025-12-07 07:21:57

web search(responses)

分析图片(chat)