SJinn: Your Ultimate Intelligent Agent for Content Creation

Generate or edit images with GPT Image 2.5 Flare and Sunburst, five aspect ratios, and 1K, 2K, or 4K output.

Models and Pricing

Model	Tool identifier	Credits per image
GPT Image 2.5 Flare	`gpt-image-2.5-api`	100
GPT Image 2.5 Sunburst	`gpt-image-2.5-sunburst-api`	120

Both tools support text-to-image generation and image editing with reference images. Every resolution has the same per-model price. An active membership and sufficient credits are required, as with the other Tool APIs.

Parameters

Send these fields inside input to POST /api/un-api/create_tool_task:

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	—	Non-empty description of the image or edit.
`image_urls`	string[]	No	`[]`	Up to 16 complete HTTP/HTTPS reference image URLs.
`image_size`	string	No	`square`	One of the five values below.
`resolution`	string	No	`1K`	`1K`, `2K`, or `4K`.

`image_size`	Aspect ratio
`square`	1:1
`portrait_4_3`	3:4
`portrait_16_9`	9:16
`landscape_4_3`	4:3
`landscape_16_9`	16:9

Unsupported sizes, resolutions, invalid reference URLs, and more than 16 references are rejected before credits are deducted. Unlimited generation is unavailable. The tool identifier selects the model and its price; no provider or model parameter is needed.

Text-to-Image Example

curl -X POST https://sjinn.ai/api/un-api/create_tool_task \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool_type": "gpt-image-2.5-api",
    "input": {
      "prompt": "A ceramic coffee cup on a sunlit wooden table",
      "image_size": "landscape_4_3",
      "resolution": "2K"
    }
  }'

Image Editing Example

curl -X POST https://sjinn.ai/api/un-api/create_tool_task \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool_type": "gpt-image-2.5-sunburst-api",
    "input": {
      "prompt": "Replace the background with a snowy mountain landscape",
      "image_urls": ["https://example.com/photo.jpg"],
      "image_size": "portrait_4_3",
      "resolution": "4K"
    }
  }'

Query the Result

A successful creation returns a task ID:

{
  "success": true,
  "errorMsg": "",
  "error_code": 0,
  "data": { "task_id": "YOUR_TASK_ID" }
}

Use that ID with the existing status endpoint:

curl "https://sjinn.ai/api/un-api/query_tool_task_status?task_id=YOUR_TASK_ID" \
  -H "Authorization: Bearer YOUR_API_KEY"

The response uses data.status: 0 for pending, 1 for completed, and 2 for failed. Completed images appear in data.output_urls; failed tasks include data.error.

See the Tool API reference for the full response format.