GPT Image 2.5 Flare Edit

Name: OpenAI GPT Image 2.5 Flare Edit
Price: 0.07875 USD
Availability: InStock
Author: OpenAI

Setup guide View SandBase Skill

25% OFFopenai/gpt-image-2.5-flare/edit

GPT Image 2.5 Flare Edit is optimized for fast, high-quality image editing and multi-image composition.

Try the model

Playground

Open playground

Input

Images(array)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

The URLs of the images to use for image-to-image generation or image editing.

Prompt(string)

The text prompt to generate an image from.

Additional Settings More

Customize your input with more control.

Quality(string)

Rendering quality. `xhigh` and `max` add detail at higher latency and cost. Allowed values: low, medium, high, xhigh, max.

Resolution(string)

The resolution of the generated image. Leave unset to preserve the provider's standard dimensions. Allowed values: 1k, 2k, 4k.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png, webp.

25% OFF

Result

Example

What would you like to do next?
Open original

Examples

Select an example to load its inputs and result into the playground.

Input

{
  "aspect_ratio": "16:9",
  "images": [
    "https://static.sandbase.ai/examples/3d800313-e314-4b73-b077-338c4e480f05/input/59dc1c2e-d32e-4373-973a-e3774421951f.png"
  ],
  "prompt": "Create a realistic billboard mockup of the shampoo on a highway scene during sunset.\nBillboard text (EXACT, verbatim, no extra characters):\n\"Fresh and clean\"\nTypography: bold sans-serif, high contrast, centered, clean kerning.\nEnsure text appears once and is perfectly legible.\nNo watermarks, no logos."
}

Open result ↗

Input

{
  "aspect_ratio": "16:9",
  "images": [
    "https://static.sandbase.ai/examples/0e28f4cf-6cda-4abe-97ba-0a003d2bea1e/input/a49736c0-87a7-4bbb-b2a7-30136569bed5.png"
  ],
  "prompt": "Turn this drawing into a photorealistic image.\nPreserve the exact layout, proportions, and perspective.\nChoose realistic materials and lighting consistent with the sketch intent.\nDo not add new elements or text."
}

Open result ↗

Input

{
  "aspect_ratio": "16:9",
  "images": [
    "https://static.sandbase.ai/examples/0e39dfef-6acd-4cc3-b89e-941defe58897/input/36bc1a5d-627c-4ef0-8f14-24a267fceb34.jpeg"
  ],
  "prompt": "In this room photo, replace ONLY white with chairs made of wood.\nPreserve camera angle, room lighting, floor shadows, and surrounding objects.\nKeep all other aspects of the image unchanged.\nPhotorealistic contact shadows and fabric texture."
}

Open result ↗

Input

{
  "images": [
    "https://static.sandbase.ai/examples/252f4520-5a86-4751-9ac0-7df448a41974/input/ea1dddac-515c-43bf-94de-768d9b69ebe2.png",
    "https://static.sandbase.ai/examples/252f4520-5a86-4751-9ac0-7df448a41974/input/42a9f30a-828b-4e7c-ae56-9ecdaffec082.png",
    "https://static.sandbase.ai/examples/252f4520-5a86-4751-9ac0-7df448a41974/input/4f11da88-1885-4b3a-a32d-09715f765ec1.png",
    "https://static.sandbase.ai/examples/252f4520-5a86-4751-9ac0-7df448a41974/input/98e8110a-07a6-41b4-a733-7391365c82c7.png"
  ],
  "output_format": "png",
  "prompt": "Create a premium photorealistic spa bathroom scene using all four products from the reference images.\n\nArrange the body lotion, artisan soap, incense burner, and bath bomb together on a natural stone vanity beside a softly steaming bathtub. Add neatly folded white towels, a small eucalyptus branch, warm candlelight, and subtle morning sunlight coming through a frosted window.\n\nPreserve the recognizable shape, material, color, proportions, and visible label details of every referenced product. Each of the four products must appear exactly once and remain clearly visible.\n\nUse an elegant editorial product-photography composition with realistic reflections, soft shadows, shallow depth of field, and refined neutral colors. The result should feel luxurious, calm, cohesive, and suitable for a premium wellness campaign.\n\nDo not use a gift basket, gift box, ribbon, or additional branded products. Do not duplicate, merge, deform, or obscure any referenced item. No extra text, no watermark, and no unrelated logos.",
  "quality": "high"
}

Open result ↗

Human preference

Arena

Elo ratings from blind side-by-side votes, compared with other image and video models.

Rankings sourced from Artificial Analysis Arena

Leaderboard: Image Editing
Rank: #3 of 77
Elo: 1182 ±11
Gap to #1: −17

Image-editing arena: people pick the better of two edits of the same image and instruction, without seeing the model names.

#1GPT Image 2.5 Sunburst (max)OpenAIOn SandBase1199±11
#2MAI-Image-2.7-PreviewMicrosoft AI1193±15
#3GPT Image 2.5 Flare (max)OpenAIThis model1182±11
#4Krea 3 (Ultra)Krea1151±14
#5MAI-Image-2.6Microsoft AI1151±12
#6Nano Banana 2.1Google1151±13
#7MAI-Image-2.6-FlashMicrosoft AI1144±13
#8GPT Image 2 (high)OpenAIOn SandBase1136±13
#9Seedream 5.0 ProByteDance SeedOn SandBase1131±13
#10Muse ImageMeta1129±12

GPT Image 2.5 Flare Edit

GPT Image 2.5 Flare edit: fast edits and multi-image composition with GPT Image 2.5.

Fields

Field	Type	Default	Notes
`images`	image URL[], required	—	Images to edit or combine, Image 1, Image 2, …
`prompt`	string, required	—	Up to 50,000 characters.
`quality`	`low` / `medium` / `high` / `xhigh` / `max`	`high`	Higher quality costs more; `high` is the default.
`resolution`	`1k` / `2k` / `4k`	—	Output size tier; omit for 1K.
`aspect_ratio`	`1:1` / `1:2` / `2:1` / `1:3` / `3:1` / `2:3` / `3:2` / `3:4` / `4:3` / `4:5` / `5:4` / `9:16` / `16:9` / `9:21` / `21:9`	—	Omit to follow the first input image.
`output_format`	`jpeg` / `png` / `webp`	`png`	Output file format.

Billing

Price depends on quality and resolution, per output image, plus $0.015 for each input image after the first:

Quality, 1 input	1k	2k	4k
low	$0.025	$0.035	$0.045
medium	$0.039	$0.055	$0.085
high (default)	$0.105	$0.165	$0.285
xhigh	$0.175	$0.285	$0.495
max	$0.375	$0.615	$1.015

Failed runs are not charged.

Prompting

Say which image is the base and what each other image adds.
List what must not change.

Limits

One output image per request.

Also on SandBase

Other GPT Image endpoints: openai/gpt-image-2.5-sunburst, openai/gpt-image-2.5-sunburst/edit, openai/gpt-image-2.5-flare, openai/gpt-image-2, openai/gpt-image-2/edit.

Start building

Send your first request

Submit this model through the SandBase Unified Run API.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

openai/gpt-image-2.5-flare/edit

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "openai/gpt-image-2.5-flare/edit",
  "images": [
    "https://cdn.openai.com/API/docs/images/body-lotion.png",
    "https://cdn.openai.com/API/docs/images/soap.png",
    "https://cdn.openai.com/API/docs/images/incense-kit.png",
    "https://cdn.openai.com/API/docs/images/bath-bomb.png"
  ],
  "prompt": "Generate a photorealistic image of a gift basket on a white background labeled 'Relax & Unwind' with a ribbon and handwriting-like font, containing all the items in the reference pictures.",
  "quality": "high",
  "output_format": "png"
}
SANDBASE_JSON
)
printf '%s\n' "$result"

2. Authentication

Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.

API key environment variable

export SANDBASE_API_KEY="YOUR_API_KEY"

Keep the key on your server. Do not expose it in browser code or commit it to a repository.

4. Files

Hosted files

Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.

Uploading images

Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.

5. Schema

Input

`images`arrayrequired

The URLs of the images to use for image-to-image generation or image editing.

`prompt`stringrequired

The text prompt to generate an image from.

Default: "Generate a photorealistic image of a gift basket on a white background labeled 'Relax & Unwind' with a ribbon and handwriting-like font, containing all the items in the reference pictures."

`quality`string

Rendering quality. `xhigh` and `max` add detail at higher latency and cost.

Default: "high"

Possible values: "low", "medium", "high", "xhigh", "max"

`resolution`string

The resolution of the generated image. Leave unset to preserve the provider's standard dimensions.

Possible values: "1k", "2k", "4k"

`aspect_ratio`string

The aspect ratio of the generated image.

Possible values: "1:1", "1:2", "2:1", "1:3", "3:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "9:21", "21:9"

`output_format`string

The format of the generated image.

Default: "png"

Possible values: "jpeg", "png", "webp"

Request body

{
  "model": "openai/gpt-image-2.5-flare/edit",
  "images": [
    "https://cdn.openai.com/API/docs/images/body-lotion.png",
    "https://cdn.openai.com/API/docs/images/soap.png",
    "https://cdn.openai.com/API/docs/images/incense-kit.png",
    "https://cdn.openai.com/API/docs/images/bath-bomb.png"
  ],
  "prompt": "Generate a photorealistic image of a gift basket on a white background labeled 'Relax & Unwind' with a ribbon and handwriting-like font, containing all the items in the reference pictures.",
  "quality": "high",
  "output_format": "png"
}

Output

A completed run exposes its result in output. The following is the model’s saved example, not a new generation.

Example output JSON

[
  {
    "source": "OpenAI Cookbook prompt (MIT)",
    "source_url": "https://developers.openai.com/cookbook/examples/multimodal/image-gen-models-prompting-guide",
    "url": "https://static.sandbase.ai/examples/3d800313-e314-4b73-b077-338c4e480f05/output/6c6b7aac-79ef-4928-b79e-bff0bea45964.png"
  }
]

GPT Image 2.5 Flare Edit

Playground

Examples

Arena

GPT Image 2.5 Flare Edit

Fields

Billing

Prompting

Limits

Also on SandBase

Send your first request

2. Authentication

4. Files

Hosted files

Uploading images

5. Schema

Input

imagesarrayrequired

promptstringrequired

qualitystring

resolutionstring

aspect_ratiostring

output_formatstring

Output

GPT Image 2.5 Sunburst Edit ↗

GPT Image 2 Edit ↗

GPT Image 1 Mini Edit ↗

GPT Image 1.5 Edit ↗

GPT Image 2 Text to Image ↗

GPT Image 2.5 Flare Text to Image ↗

`images`arrayrequired

`prompt`stringrequired

`quality`string

`resolution`string

`aspect_ratio`string

`output_format`string