Image Generation

The Grok Image image generation endpoint. Submits a generation task from a prompt. The interface is async: on success it returns an image.task object; poll the Query Result endpoint with the returned task ID until status becomes completed to fetch the final image.

Billing model

This endpoint is billed under the model specified by the model field (grok-imagine-1.0 / grok-imagine-2.0 / grok-imagine-image / grok-imagine-image-quality / grok-imagine-image-2.0), and the fee is deducted from your account balance.

Async flow

POST /v1/images/async/generations submits the task and returns task_id (prefixed with task_) and status=queued/in_progress;
Poll GET /v1/images/async/generations/{task_id} with that task_id;
When status=completed, the data array contains the final image URL (url field); when failed, error explains why.

Images are kept for about 2 hours

The returned image URL is temporary (metadata.assetsExpireAt holds the expiry time in Unix seconds); images are kept for about 2 hours and then deleted automatically. Download them before they expire if you need long-term storage.

Authorization

BearerAuth

AuthorizationBearer <token>

使用 Bearer Token 认证。格式: Authorization: Bearer sk-xxxxxx 令牌需开通对应模型的调用权限。

In: header

Request Body

application/json

model*string

模型名称，可选：grok-imagine-1.0、grok-imagine-2.0、grok-imagine-image、grok-imagine-image-quality、grok-imagine-image-2.0

prompt*string

提示词，描述希望生成的图片内容

n?integer

生成数量（1-4），默认 1

Range1 <= value <= 4

size?string

输出比例。可传 OpenAI 风格尺寸（如 1024x1024、1536x1024、1024x1536），网关会映射为最接近的宽高比；也可直接传宽高比（如 1:1、16:9、9:16、3:2、2:3）。grok-imagine-1.0 / grok-imagine-2.0 仅支持基础比例，Grok Image 系列支持更多比例（含 auto）。不传默认 1:1

quality?string

画质：low / medium。仅 grok-imagine-image-2.0 支持；其余模型忽略该字段

Value in"low" | "medium"

Response Body

application/json

curl -X POST "https://www.omwai.xyz/v1/images/async/generations" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine-2.0",
    "prompt": "a cute cat, cyberpunk style, neon background",
    "size": "1024x1024",
    "n": 1
  }'

curl -X POST "https://www.omwai.xyz/v1/images/async/generations" \  -H "Content-Type: application/json" \  -d '{    "model": "grok-imagine-2.0",    "prompt": "a cute cat, cyberpunk style, neon background",    "size": "1024x1024",    "n": 1  }'

{
  "id": "task_01J8ABCDEFGHIJKLMNOPQRST",
  "task_id": "task_01J8ABCDEFGHIJKLMNOPQRST",
  "object": "image.task",
  "model": "grok-imagine-2.0",
  "status": "queued",
  "progress": "20%",
  "created_at": 1788256630,
  "completed_at": 1788256720
}

{
  "code": "invalid_request",
  "message": "string"
}

{
  "code": "string",
  "message": "string"
}

Note

A successful submission (HTTP 200) only means the task was accepted, not that the image is ready. Always poll the query endpoint until status=completed.

Image Generation

Authorization

Request Body

Response Body

200application/json

400application/json

401application/json

application/json

application/json

application/json