GPT Image 2.5 Flare API: Image Generation & Editing

Overview

GPT Image 2.5 Flare is an asynchronous image generation API for text-to-image and reference-guided image editing.

Current implementation notice: GPT Image 2.5 Flare currently provides the GPT Image 2 capability baseline. Its public model ID, accepted parameters, and prices are listed on this page.

Capability	Value
Model ID	`gpt-image-2.5-flare`
Modes	`text-to-image`, `image-to-image`
Prompt length	1-20,000 characters
Reference images	1-16 URLs for `image-to-image`
Aspect ratios	`auto`, `1:1`, `1:2`, `2:1`, `2:3`, `3:2`, `4:3`, `3:4`, `4:5`, `5:4`, `16:9`, `9:16`, `21:9`
Output control	`aspect_ratio` or custom `WIDTHxHEIGHT` `size`
Resolution tiers	`1k`, `2k`, `4k`
Quality tiers	`low`, `medium`, `high`, `xhigh`, `max`

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/gpt-image-2.5-flare`	Submit a generation task
`GET`	`/statusTask/gpt-image-2.5-flare?taskId={taskId}`	Poll task status and retrieve results

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Quickstart

curl -X POST "https://api.apixo.ai/api/v1/generateTask/gpt-image-2.5-flare" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-image",
      "prompt": "A premium minimalist perfume bottle on dark green marble, soft studio lighting, luxury commercial photography, no text",
      "aspect_ratio": "1:1",
      "resolution": "1k",
      "quality": "medium"
    }
  }'

The accepted response includes data.taskId. Save it and poll until state becomes success or failed.

Request body

Text-to-image

{
  "request_type": "async",
  "input": {
    "mode": "text-to-image",
    "prompt": "A cinematic aerial view of a coastal city at sunrise, warm golden light, realistic clouds and ocean, no text",
    "aspect_ratio": "16:9",
    "resolution": "2k",
    "quality": "high"
  }
}

Image-to-image

{
  "request_type": "async",
  "input": {
    "mode": "image-to-image",
    "prompt": "Transform the supplied product photo into a clean premium e-commerce hero image with a white studio background. Preserve the product shape and logo.",
    "image_urls": [
      "https://your-domain.com/images/product-source.png"
    ],
    "size": "1536x1024",
    "resolution": "2k",
    "quality": "xhigh"
  }
}

Parameters

string

default:"async"

required

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

string

Required when request_type is callback. It must be a public HTTPS URL that can receive the final task payload. See Webhooks.

object

required

GPT Image 2.5 Flare input parameters.

Show properties

string

required

Generation mode. Supported values: text-to-image, image-to-image.

string

required

Text prompt describing the requested image or edit. Supports 1-20,000 characters.

string[]

Publicly accessible reference image URLs. Required for image-to-image; supports 1-16 URLs.

string

default:"auto"

Output aspect ratio. Supported values: auto, 1:1, 1:2, 2:1, 2:3, 3:2, 4:3, 3:4, 4:5, 5:4, 16:9, 9:16, 21:9. Ignored when size is supplied.

string

Optional custom output size in WIDTHxHEIGHT format, such as 1536x1024. Takes priority over aspect_ratio.

string

default:"1k"

Output resolution tier. Supported values: 1k, 2k, 4k.

string

default:"medium"

Quality and billing tier. Supported values: low, medium, high, xhigh, max. Each tier has its own listed price.

Poll for results

curl -X GET "https://api.apixo.ai/api/v1/statusTask/gpt-image-2.5-flare?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

When successful, data.resultJson is a JSON string containing resultUrls:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/xxx.png\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

For failed tasks, state is failed and the response includes failCode and failMsg.

Billing

Billing is per successfully generated image. Prices below are in USD and retain four decimal places.

Quality	`1k`	`2k`	`4k`
`low`	`$0.0360`	`$0.0480`	`$0.0660`
`medium`	`$0.0509`	`$0.0538`	`$0.0970`
`high`	`$0.2026`	`$0.2132`	`$0.3850`
`xhigh`	`$0.3039`	`$0.3197`	`$0.5775`
`max`	`$0.3647`	`$0.3837`	`$0.6930`

For the live price catalog, see Pricing.

Latency and polling

Generation time depends on prompt complexity, reference images, selected resolution, and current queue load. Start polling after 30-60 seconds, then poll every 10 seconds. For production workloads, prefer callback mode.

​Overview

​Endpoint and authentication

​Quickstart

​Request body

​Text-to-image

​Image-to-image

​Parameters

​Poll for results

​Billing

​Latency and polling

​Related links

Overview

Endpoint and authentication

Quickstart

Request body

Text-to-image

Image-to-image

Parameters

Poll for results

Billing

Latency and polling

Related links