{
"created": 1700000000,
"data": [
{
"url": "https://cdn.example.com/image.png"
}
]
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}Generate images
Request format, responses, and capability boundaries.
{
"created": 1700000000,
"data": [
{
"url": "https://cdn.example.com/image.png"
}
]
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}POST /v1/images/generations
Send JSON with model and prompt. Start with one image; dimensions, quality, and response representation must match the selected model.
Read data[].url or data[].b64_json on success. This reference covers synchronous results. Streaming-capable relay channels need their image event protocol; task plugins have no universal streaming mode. Inspect logs before resubmitting after a timeout.
Integration guide and runnable example
简体中文Authorizations
模型调用 API Key，不是控制台登录凭据 / Model API key, not console login credentials
Body
当前密钥可用且支持此接口的模型 ID / Model ID available to the key and supporting this endpoint
"YOUR_MODEL_ID"
任务描述；遵循模型的长度和内容要求 / Task description; follow model length and content requirements
请求图片数，模型通常有更小限制；建议从 1 开始 / Requested image count; models usually impose a smaller limit; start with 1
1 <= x <= 128模型支持的尺寸，使用 x 而不是 × / Model-supported size; use x rather than ×
质量档位，由模型决定 / Quality setting determined by the model
url 或 b64_json，仅在模型支持时指定；有些模型固定返回 Base64 / url or b64_json when supported; some models always return Base64
输出编码，例如 png、jpeg、webp；需模型支持 / Output encoding such as png, jpeg, webp; requires model support
背景选项；透明背景需模型和编码支持 / Background option; transparency requires model and format support