GPT Image 2.5 Reverse

POST

tasks

curl --request POST \
  --url https://api.qingbo.ai/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "image_urls": [
    "<string>"
  ],
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "n": 123
}
'

import requests

url = "https://api.qingbo.ai/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "n": 123
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    image_urls: ['<string>'],
    aspect_ratio: '<string>',
    resolution: '<string>',
    n: 123
  })
};

fetch('https://api.qingbo.ai/v1/tasks', 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://api.qingbo.ai/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123\n}")

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

	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))

}

HttpResponse<String> response = Unirest.post("https://api.qingbo.ai/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123\n}")
  .asString();

GPT Image 2.5 Reverse provides GPT Image 2.5 text-to-image generation and reference-image editing through an aggregator, covering two models: gpt-image-2.5-flare-rev (Flare, faster output) and gpt-image-2.5-sunburst-rev (Sunburst, favouring editing precision). Their request parameters, value ranges and rates are identical, and pricing is fixed by output resolution, which suits everyday imagery, visual drafts and product assets on a fixed per-image budget. Switching between them means changing the model field alone.

This is a reverse line, not the official OpenAI API. Use GPT Image 2.5 Official for quality levels, masks, transparent backgrounds, and output-format controls. QWave never switches between the two lines automatically.

Quick start

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: image25-rev-001" \
  -d '{
    "model": "gpt-image-2.5-flare-rev",
    "action": "generate",
    "prompt": "A sky garden in a futuristic city, early morning mist, architectural photography",
    "aspect_ratio": "16:9",
    "resolution": "2k",
    "n": 1
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: image25-rev-edit-001" \
  -d '{
    "model": "gpt-image-2.5-sunburst-rev",
    "action": "edit",
    "prompt": "Preserve the product and its package text, replace the background with a soft off-white studio, and add a natural shadow",
    "image_urls": ["https://cdn.example.com/source.png"],
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "n": 1
  }'

A successful submission returns a task_id. Retrieve the result with GET /v1/tasks/{task_id}, wait inline with Prefer: wait, or configure a webhook.

Request parameters

string

required

gpt-image-2.5-flare-rev or gpt-image-2.5-sunburst-rev.

string

default:"generate"

generate: create an image from text
edit: edit reference images; requires image_urls

string

required

The image description or editing instruction.

string[]

Reference image URLs. Required for edit; up to 16 images. References do not add a fee.

string

default:"1:1"

One of auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, or 21:9. auto lets the model choose the ratio from the content.

string

default:"1k"

Output resolution: 1k, 2k, or 4k.

integer

default:"1"

Number of images to generate. Value: 1. Each request returns one image.

See Submit a task for callback_url, callback_events, Prefer: wait, Idempotency-Key, and the maximum-cost header. The reverse line does not support quality, mask_url, background, output_format, output_compression or moderation, which are available on the official line only; seed is not supported either. Any other parameter returns 400 and is not billed.

Limits

Condition	Limit
Per request	One image
`action: "edit"`	At least one reference image is required
Reference images	Up to 16

Pricing

Successful images are billed at a fixed price per image, with a different rate at 1k, 2k and 4k; both models carry the same rates. Rates are in price_config on GET /v1/models and in the console’s Model Market. What a single call actually cost is the cost field on the task response — an integer quota at 500,000 quota = 1 USD, not dollars. generate and edit cost the same, reference images add no fee, and neither aspect ratio nor prompt length changes the price — resolution is the only billing dimension, so the cost of a call is known before it is sent. When resolution is omitted, the image is generated at the default 1k and billed at the 1k rate. Only a successfully generated image is billed. Failed and cancelled tasks, and tasks that return no usable image, are refunded in full.

Response

Completed task

{
  "task_id": "task-wave1789004688b950049238",
  "model": "gpt-image-2.5-flare-rev",
  "action": "generate",
  "status": "completed",
  "progress": "100%",
  "result": {
    "images": [
      {
        "url": ["https://cdn.example.com/result.png"],
        "expires_at": 1789568757
      }
    ]
  },
  "billing_status": "settled",
  "cost": 4781
}

result.images carries the generated image, and expires_at is when that link is deleted (artifacts are kept for 7 days). The full field reference is in Task status.

Available models

Model ID	Trade-off	Suited to	Billing
`gpt-image-2.5-flare-rev`	Flare, faster output	Everyday imagery, batch visual drafts	Fixed by resolution
`gpt-image-2.5-sunburst-rev`	Sunburst, editing precision first	Product assets, detailed edits	Fixed by resolution

Both models share the same parameters, value ranges and rates; only the generated result differs. Every section of this page applies to both.

Official vs reverse

	Reverse	Official
Model IDs	`gpt-image-2.5-flare-rev` `gpt-image-2.5-sunburst-rev`	`gpt-image-2.5-flare` `gpt-image-2.5-sunburst`
Access	Aggregator reverse line	Official API line
Billing	Fixed by resolution	Actual token usage
Generation / reference editing	Supported, up to 16 references	Supported, up to 16 references
Aspect ratios	`auto` plus 10	15, including `2:1` `1:2` `3:1` `1:3` `9:21`, no `auto`
Quality levels	Not supported	`low` / `medium` / `high` / `xhigh` / `max`
Mask inpainting	Not supported	Supported
Background and output format	Not supported	Supported
Output count	1	1

GPT Image 2.5 Reverse

curl --request POST \
  --url https://api.qingbo.ai/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "image_urls": [
    "<string>"
  ],
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "n": 123
}
'

import requests

url = "https://api.qingbo.ai/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "n": 123
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    image_urls: ['<string>'],
    aspect_ratio: '<string>',
    resolution: '<string>',
    n: 123
  })
};

fetch('https://api.qingbo.ai/v1/tasks', 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://api.qingbo.ai/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123\n}")

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

	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))

}

HttpResponse<String> response = Unirest.post("https://api.qingbo.ai/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123\n}")
  .asString();

Text Generation

Image Generation

Video Generation

Audio

Tools & Embeddings

Task Management

Account & Usage

GPT Image 2.5 Reverse

Quick start

Request parameters

Limits

Pricing

Response

Available models

Official vs reverse

​Quick start

​Request parameters

​Limits

​Pricing

​Response

​Available models

​Official vs reverse

​Related

Quick start

Request parameters

Limits

Pricing

Response

Available models

Official vs reverse

Related