Create image task - AI Platform

POST

images

Create image task

curl --request POST \
  --url https://sigrunai.com/v1/images \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2",
  "prompt": "极简产品静物，白色背景，柔光",
  "quality": "medium",
  "n": 1,
  "ratio": "1:1"
}
'

import requests

url = "https://sigrunai.com/v1/images"

payload = {
    "model": "gpt-image-2",
    "prompt": "极简产品静物，白色背景，柔光",
    "quality": "medium",
    "n": 1,
    "ratio": "1:1"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-image-2',
    prompt: '极简产品静物，白色背景，柔光',
    quality: 'medium',
    n: 1,
    ratio: '1:1'
  })
};

fetch('https://sigrunai.com/v1/images', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://sigrunai.com/v1/images"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2\",\n  \"prompt\": \"极简产品静物，白色背景，柔光\",\n  \"quality\": \"medium\",\n  \"n\": 1,\n  \"ratio\": \"1:1\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

{
  "code": 20000,
  "msg": "<string>",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "progress": 123,
    "model": "<string>",
    "created_at": 123,
    "completed_at": 123,
    "cost": 123,
    "error_message": "<string>",
    "result": {
      "image_url": "<string>",
      "video_url": "<string>"
    }
  }
}

Create an async GPT Image 2 task. Poll with Query image task and read result.image_url when completed.

Models

`model`	Notes	Billing
`gpt-image-2`	Preferred; pick tier via `quality`	see below
`gpt-image-2-low`	Low tier	`per_task`
`gpt-image-2-medium`	Medium tier	`per_task`
`gpt-image-2-high`	High tier	`per_task`

If model is gpt-image-2 and quality is low / medium / high, billing uses the matching gpt-image-2-* model. Default quality is auto.

Request body

Field	Type	Required	Description
`model`	string	yes	See table above
`prompt`	string	yes	1–4000 characters
`quality`	string	no	`auto` (default), `low`, `medium`, `high`
`n`	int	no	1–4 images, default 1; cost × count
`ratio`	string	no	Aspect ratio; `size` is an alias
`size`	string	no	Alias of `ratio`
`resolution`	string	no	Optional hint (e.g. `1k` / `2k`)
`images`	string[]	no	Public reference image URLs, max 15

Example

curl -X POST 'https://sigrunai.com/v1/images' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-image-2",
    "prompt": "Minimal product still life, white background, soft light",
    "quality": "medium",
    "n": 1,
    "ratio": "1:1"
  }'

Success response:

{
  "code": 20000,
  "msg": "提交成功",
  "data": {
    "task_id": "img_xxxxxxxx",
    "status": "queued",
    "progress": 0,
    "model": "gpt-image-2",
    "cost": 0.2,
    "result": {}
  }
}

Authorizations

Authorization

string

header

required

API key from the console. Format: Bearer sk_xxx

Body

application/json

model

string

required

gpt-image-2 或 gpt-image-2-low / medium / high

Example:

"gpt-image-2"

prompt

string

required

Required string length: 1 - 4000

quality

enum<string>

default:auto

Available options:

auto,

low,

medium,

high

integer

default:1

Required range: 1 <= x <= 4

ratio

string

size

string

ratio 别名

resolution

string

images

string<uri>[]

Maximum array length: 15

Response

200 - application/json

提交成功

code

integer

Example:

20000

msg

string

data

object

Show child attributes

⌘I

Create image task

curl --request POST \
  --url https://sigrunai.com/v1/images \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2",
  "prompt": "极简产品静物，白色背景，柔光",
  "quality": "medium",
  "n": 1,
  "ratio": "1:1"
}
'

import requests

url = "https://sigrunai.com/v1/images"

payload = {
    "model": "gpt-image-2",
    "prompt": "极简产品静物，白色背景，柔光",
    "quality": "medium",
    "n": 1,
    "ratio": "1:1"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-image-2',
    prompt: '极简产品静物，白色背景，柔光',
    quality: 'medium',
    n: 1,
    ratio: '1:1'
  })
};

fetch('https://sigrunai.com/v1/images', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://sigrunai.com/v1/images"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2\",\n  \"prompt\": \"极简产品静物，白色背景，柔光\",\n  \"quality\": \"medium\",\n  \"n\": 1,\n  \"ratio\": \"1:1\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

{
  "code": 20000,
  "msg": "<string>",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "progress": 123,
    "model": "<string>",
    "created_at": 123,
    "completed_at": 123,
    "cost": 123,
    "error_message": "<string>",
    "result": {
      "image_url": "<string>",
      "video_url": "<string>"
    }
  }
}

​Models

​Request body

​Example

Authorizations

Body

Response

Models

Request body

Example