Skip to main content
POST
/
api
/
open-api
/
v1
/
images
Create Image Task
curl --request POST \
  --url https://www.jimmyai.cn/api/open-api/v1/images \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "ratio": "auto",
  "images": [
    "<string>"
  ],
  "resolution": "1k",
  "quality": "low"
}
'
{
  "code": "20000",
  "msg": "ok",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "model": "<string>",
    "created_at": 123
  }
}
This endpoint is asynchronous: it returns a task_id. Poll Query Image Task for results.For synchronous text-to-image or image edit (OpenAI-compatible, returns b64_json on success), use Text-to-Image (Sync) or Edit Image (Sync).
Async image tasks use ratio for aspect ratio (e.g. 1:1, 16:9); default is auto. Sync OpenAI-compatible endpoints (/images/generations, /images/edits) still use size for pixel dimensions (e.g. 1024x1024).

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model
string
required

Model name (supported: gpt-image-2, nano-banana, nano-banana-2, nano-banana-pro)

​
prompt
string
required

Text prompt for image generation

​
ratio
enum<string>
default:auto

Aspect ratio. Supported values: auto, 1:1 (Square), 3:2 (Landscape), 2:3 (Portrait), 4:3 (Landscape), 3:4 (Portrait), 5:4 (Landscape), 4:5 (Portrait), 16:9 (Widescreen), 9:16 (Vertical), 2:1 (Landscape), 1:2 (Portrait), 3:1 (Wide Landscape), 1:3 (Tall Portrait), 21:9 (Ultrawide), 9:21 (Ultrawide Vertical)

Available options:
auto,
1:1,
3:2,
2:3,
4:3,
3:4,
5:4,
4:5,
16:9,
9:16,
2:1,
1:2,
3:1,
1:3,
21:9,
9:21
​
images
string[]

Reference image URLs or base64 strings

​
resolution
enum<string>
default:1k

Image resolution (supported by gpt-image-2, nano-banana-2, etc.). Supported values: 1k, 2k, 4k. Note: gpt-image-2 with 4K resolution only supports the following aspect ratios: 16:9 / 9:16 / 2:1 / 1:2 / 21:9 / 9:21.

Available options:
1k,
2k,
4k
​
quality
enum<string>
default:low

Image quality (supported by gpt-image-2). Supported values: low, medium, high.

Available options:
low,
medium,
high

Response

200 - application/json

Task created successfully

​
code
string
Example:

"20000"

​
msg
string
Example:

"ok"

​
data
object