---
title: GPT-Image-2.5 Flare | Runware Docs
url: https://runware.ai/docs/models/openai-gpt-image-2-5-flare
description: Fast, high-quality image generation and editing for everyday creative production
---
# GPT-Image-2.5 Flare

![GPT-Image-2.5 Flare](https://assets.runware.ai/covers/openai-gpt-image-2-5-flare.jpg)

GPT-Image-2.5 Flare is OpenAI's fastest model for high-quality image generation and editing, delivering higher-quality images than GPT Image 2 at 50% lower latency. It improves natural lighting, texture detail, reference-subject preservation, localized editing, and consistency across iterative edits, while handling complex layouts and transparent backgrounds. It is designed for creator content, product experiences, visual search, rapid prototyping, and high-volume generation.

- **Status**: live
- **ID**: `openai:gpt-image@2.5-flare`
- Try in Playground
- **Creator**: OpenAI
- **Release Date**: September 8, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

~$0.0336 typical run

**Rates** (per 1M tokens)

- Text input: `$5.00`
- Image input: `$8.00`
- Image output: `$30.00`

**4 example generations**

- [inpaint](https://runware.ai/docs/models/openai-gpt-image-2-5-flare/examples#example-portable-microscope-colorway-product-image): `$0.0228` (~20s)
- [reference-to-image](https://runware.ai/docs/models/openai-gpt-image-2-5-flare/examples#example-adaptive-rainwear-lookbook-editorial): `$0.0241` (~19s)
- [text-to-image](https://runware.ai/docs/models/openai-gpt-image-2-5-flare/examples#example-circular-laundry-campaign-key-visual): `$0.0431` (~21s)
- [transparent-background](https://runware.ai/docs/models/openai-gpt-image-2-5-flare/examples#example-forensic-entomologist-exhibit-persona): `$0.0471` (~23s)

billed per token, so a request costs what the model produced · times vary, measured end to end · [How pricing works](https://runware.ai/docs/platform/pricing)

## Compatibility & Validation

When `inputs.maskImage` is provided, `inputs.referenceImages` is required.

---

When `settings.background` is `transparent`, `outputFormat` is limited to `PNG`, `WEBP`.

---

`width` and `height` must be used together.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-outputformat)

- **Type**: `string`
- **Required**: conditional — Required when settings.background is provided
- **Default**: `JPG`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency).
- \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel).
- \`WEBP\`: Modern format providing superior compression and transparency support.

> [!NOTE]
> \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns complete results directly in the API response.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/platform/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (1 property)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time.

### [ttl](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [maskImage](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-inputs-maskimage)

- **Path**: `inputs.maskImage`
- **Type**: `string`

Image used to specify which areas of the input image should be edited (UUID, URL, Data URI, or Base64). White marks the area to edit, black is preserved. The model treats the mask as guidance rather than a hard boundary, so edits can extend past its shape. With several reference images the mask applies to the first.

### [referenceImages](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `16`

List of reference images (UUID, URL, Data URI, or Base64).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `openai:gpt-image@2.5-flare`

Identifier of the model to use for generation.

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `32000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-width)

- **Type**: `integer`
- **Required**: true
- **Min**: `16`
- **Max**: `3840`
- **Step**: `16`

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `16`
- **Max**: `3840`
- **Step**: `16`

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [background](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-settings-background)

- **Path**: `settings.background`
- **Type**: `string`
- **Default**: `auto`

Background handling in generated images.

**Allowed values**:

- `auto` Automatically determines the most appropriate background based on content.
- `opaque` Solid background, no transparency.
- `transparent` Transparent background areas where applicable.

### [moderation](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-settings-moderation)

- **Path**: `settings.moderation`
- **Type**: `string`
- **Default**: `auto`

Content moderation level.

**Allowed values**:

- `auto` Standard filtering that limits creating certain categories of potentially age-inappropriate content.
- `low` Less restrictive filtering.

### [quality](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-settings-quality)

- **Path**: `settings.quality`
- **Type**: `string`
- **Default**: `auto`

Image quality level.

**Allowed values**: `auto` `max` `xhigh` `high` `medium` `low`

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-advancedfeatures-watermark)

- **Path**: `advancedFeatures.watermark`
- **Type**: `object (6 properties)`

Configuration object for adding watermarks to generated videos. Watermarks can be applied using either text or image content with customizable positioning and appearance. You must provide either `text` or `image` content for the watermark, but not both.

**Text watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "© 2025 Company",
    "displayPosition": "bottom-right",
    "opacity": 0.6,
    "fontColor": "#ffffff",
    "bgColor": "#000000"
  }
}
```

**Image watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "image": "c64351d5-4c59-42f7-95e1-eace013eddab",
    "displayPosition": "top-left",
    "opacity": 0.6
  }
}
```

**Tiled watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "PREVIEW",
    "tiled": true,
    "opacity": 0.4,
    "fontColor": "#cccccc"
  }
}
```

#### [text](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-advancedfeatures-watermark-text)

- **Path**: `advancedFeatures.watermark.text`
- **Type**: `string`
- **Min**: `2`
- **Max**: `32`

Watermark text.

#### [image](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-advancedfeatures-watermark-image)

- **Path**: `advancedFeatures.watermark.image`
- **Type**: `string`

Watermark image (UUID, URL, Data URI, or Base64).

#### [displayPosition](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-advancedfeatures-watermark-displayposition)

- **Path**: `advancedFeatures.watermark.displayPosition`
- **Type**: `string`

Watermark position.

**Allowed values**: `top-left` `top-center` `top-right` `center-left` `center-center` `center-right` `bottom-left` `bottom-center` `bottom-right` `tiled`

#### [opacity](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-advancedfeatures-watermark-opacity)

- **Path**: `advancedFeatures.watermark.opacity`
- **Type**: `float`
- **Min**: `0.1`
- **Max**: `1`
- **Step**: `0.01`

Watermark opacity.

#### [fontColor](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-advancedfeatures-watermark-fontcolor)

- **Path**: `advancedFeatures.watermark.fontColor`
- **Type**: `string`

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#request-advancedfeatures-watermark-bgcolor)

- **Path**: `advancedFeatures.watermark.bgColor`
- **Type**: `string`

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [imageUUID](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#response-imageuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#response-imageurl)

- **Type**: `string`
- **Format**: `uri`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#response-imagedatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output image.

### [seed](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/openai-gpt-image-2-5-flare#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-image (text-to-image)

![Circular Laundry Campaign Key Visual](https://assets.runware.ai/examples/openai-gpt-image-2-5-flare/dcc0b014-49f2-423c-8305-7b64176d8556.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "8df35950-2168-40aa-a31d-bce988b18f29",
  "model": "openai:gpt-image@2.5-flare",
  "positivePrompt": "Create a finished brand marketing campaign key visual for a company that builds closed-loop water-recycling systems for large commercial laundries. Depict a vast, immaculate industrial laundry and water-treatment facility with stainless-steel filtration vessels, orderly pipework, grated walkways, gauges, and subtle condensation. The central visual metaphor is a single enormous pristine white hotel sheet sweeping through the space in a graceful airborne arc like a cresting wave. At the lowest point of the fabric, its folds transition seamlessly and believably into a stream of crystal-clear water flowing into a circular filtration tank. Show one real environmental engineer in ultramarine coveralls standing on the right-side walkway, seen at a modest scale while inspecting the system, providing human scale without posing for the camera.\n\nUse premium large-format advertising photography with sophisticated practical set design and restrained photoreal compositing. Preserve convincing cotton weave, damp fabric edges, transparent water, tiny droplets, brushed steel, glass inspection ports, and realistic industrial construction. Cool daylight enters from clerestory windows and creates long soft beams through faint clean mist, balanced by warm practical indicator lights. Color palette: chalk white, stainless silver, deep ultramarine, pale mineral cyan, with only tiny amber accents. The mood is intelligent, calm, optimistic, and materially honest rather than futuristic.\n\nCompose in 3:2 landscape for a campaign master image. Place the dramatic fabric-and-water arc from upper center toward the lower right, leading the eye to the engineer and filtration tank. Keep the left third visually quieter with softly illuminated architectural depth and controlled negative space for optional campaign copy to be added later. Maintain a strong silhouette and clear visual hierarchy at billboard distance while retaining rich engineering detail up close. No written words, logos, labels, symbols, watermark, border, poster frame, user interface, or mockup. Do not add excessive greenery, sci-fi holograms, fantasy machinery, or implausible floating equipment.",
  "width": 1536,
  "height": 1024
}
```

---

### reference-to-image (reference-to-image)

![Adaptive Rainwear Lookbook Editorial](https://assets.runware.ai/examples/openai-gpt-image-2-5-flare/1ff70034-e519-41ff-adf8-0da0b31361ad.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "47b0147a-8e04-4574-8d46-34d2f14e800c",
  "model": "openai:gpt-image@2.5-flare",
  "positivePrompt": "Create a new, finished square fashion lookbook photograph for a premium adaptive outerwear collection. Use both reference images as complementary guidance rather than reproducing either source: preserve the specific garment design, material, deep-aubergine color, sculpted hood, asymmetric magnetic closure, storm flap, reflective piping, articulated sleeves, and extended lap-covering front panel from reference 1; draw the waterfront architecture, wet-concrete textures, cool cyan and warm amber lighting contrast, misty atmosphere, and restrained palette from reference 2. Place the garment on a stylish adult wheelchair user with a contemporary short haircut, seated naturally in a sleek manual wheelchair at the ferry terminal. Show an authentic, practical fit around the seated body and chair without obscuring the garment's key construction details. The model faces three-quarters toward camera with a calm, self-possessed expression, one hand resting lightly on the wheel rim. Compose as a polished catalog hero image: full seated figure visible from hood to wheels, centered slightly left, generous architectural negative space, eye-level camera, crisp editorial geometry, realistic proportions, and no cropping of the chair. Soft misty daylight provides broad fill while a single amber fixture creates a subtle edge light; wet pavement gives a restrained reflection. Emphasize premium waterproof textile texture, fine seams, hardware, realistic skin, and accurate wheelchair structure. Sophisticated, quiet, functional, inclusive fashion direction; modern European lookbook photography; no brand name, logos, captions, typography, signage, extra people, duplicated limbs, or decorative fantasy elements. The final image must be an original synthesis with a new model, pose, viewpoint, and composition, not a copy of either reference.",
  "width": 1024,
  "height": 1024,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/e2bf6a65-bc4b-40ec-865c-257b566c0f63.jpg",
      "https://assets.runware.ai/assets/inputs/6731cad8-3970-430a-9d30-2d6eeeedeb1d.jpg"
    ]
  }
}
```

---

### inpaint (inpaint)

![Portable Microscope Colorway Product Image](https://assets.runware.ai/examples/openai-gpt-image-2-5-flare/5d9ec2ef-db26-4cca-b500-5c37f5ec98c0.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "d0623f3e-1345-4f90-a0b5-066cd3f3cd8b",
  "model": "openai:gpt-image@2.5-flare",
  "positivePrompt": "Using the reference image and mask, create a production-ready ecommerce colorway variant of the same portable field microscope. Replace the entire masked microscope while faithfully preserving its exact silhouette, proportions, industrial design, viewing angle, position, lens arrangement, handle, controls, base geometry, and scale. Change the main molded housing to a sophisticated matte celadon green; render the structural metal components in warm champagne anodized aluminum; make the focus knobs, eyepiece surround, base grip, and small functional accents deep oxblood red. Keep optical glass dark and realistic with restrained blue-green reflections. Materials must look physically manufactured, with precise seams, subtle microtexture, crisp edges, and natural tonal variation rather than flat digital color. Preserve the original continuous light-gray studio background, camera perspective, soft diffused lighting, contact points, and coherent cast shadow. The finished image should feel like an approved limited-edition product colorway photograph for a scientific equipment catalog: clean, premium, technically credible, centered portrait composition, no added accessories, no packaging, no people, no text, no logo, and no changes outside the product.",
  "width": 1024,
  "height": 1280,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/8ab73d91-132b-4996-9de0-06e983958255.jpg"
    ],
    "maskImage": "https://assets.runware.ai/assets/inputs/44ebca73-ed8b-4091-be14-a4aff8a216be.png"
  }
}
```

---

### transparent-background (transparent-background)

![Forensic Entomologist Exhibit Persona](https://assets.runware.ai/examples/openai-gpt-image-2-5-flare/af39b964-d88c-4978-8912-41eef592681c.png)

```json
{
  "taskType": "imageInference",
  "taskUUID": "18482929-d764-400b-965b-519427c49985",
  "outputFormat": "PNG",
  "model": "openai:gpt-image@2.5-flare",
  "positivePrompt": "Create a definitive full-body character portrait for a natural-history museum exhibit persona: Dr. Nia Okafor, a confident Black British forensic entomologist in her early 40s. She has deep brown skin, an oval face, alert dark eyes behind translucent hexagonal glasses, and short natural coils with one narrow silver streak above her right temple. Her distinctive outfit is a tailored aubergine field vest over a bone-colored rolled-sleeve shirt, straight dark olive utility trousers, chartreuse socks, and practical rust-red lace-up field boots. Include a small silver beetle brooch on the vest as her recurring character marker. She stands in a relaxed three-quarter pose, facing the viewer with a warm, quietly authoritative expression. One hand holds a compact transparent specimen case containing a few clearly visible pinned beetle specimens; the other holds a slim brass magnifying loupe at her side. Art direction: sophisticated hand-cut paper collage combined with crisp editorial screen-print illustration, subtly layered paper fibers, simplified geometric shapes, precise facial likeness, limited palette of aubergine, chartreuse, bone, rust red, olive, deep brown, and small brass accents. Friendly and credible rather than cartoonish, designed for audiences ages 10 and up. Render exactly one complete character from head to boots, with both arms, both hands, and all accessories fully visible. Clean, readable outer contour with no cropped anatomy, no detached pieces, no scenery, no furniture, no border, no lettering, no logos, and no additional people or creatures outside the specimen case. Center the character within the 1280x1024 landscape canvas at a generous scale while preserving ample transparent space on every side. Transparent background, clean isolated asset, no floor, no cast shadow, no rectangular backdrop.",
  "width": 1280,
  "height": 1024,
  "settings": {
    "background": "transparent"
  }
}
```