GPT Image 2.5 Flare API

OpenAI GPT Image 2.5 Flare: fast everyday generation and editing with precise text rendering.

OpenAI·ImageAvailable

from$0.0053/ image~~$0.0059~~10% off

Model IDgpt-image-2.5-flare

Try in Playground View API

text-to-imageimage-edit

Input

Text · Image

Output

Image

Provider

6 providers

Aspect ratio

1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3

Quality

low · medium · high · xhigh · max

Images

1 – 4

Last 7 days · not enough recent requests for stats yet.

GPT Image 2.5 Flare pricing

Prices are per unit; requests without a provider are routed to the cheapest provider that supports your parameters.

Option	Price (USD)
quality: low	$0.0053 / image 1 Credits
quality: medium	$0.012 / image 2 Credits
quality: high	$0.047 / image 5 Credits
quality: xhigh	$0.084 / image 9 Credits
quality: max	$0.19 / image 19 Credits

Try GPT Image 2.5 Flare before you integrate

Test output quality, compare provider prices and estimate cost before writing any code.

Provider

Image

Estimated cost

Input

Prompt*prompt

Reference imagesimage_urls

Aspect ratioaspect_ratio

Qualityquality

Imagesnum_images

Result

Idle

Your generation will appear here.

Provider prices for this request

Enter a prompt to compare provider prices.

GPT Image 2.5 Flare prompt examples

Ready-to-use prompts. Load one into the playground and tweak it.

Source

Scene

11 prompts

create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W

create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912

A stylish young European woman standing in front of a premium retro-futuristic booksto

A stylish young European woman standing in front of a premium retro-futuristic bookstore at night, wearing a sharp black coat and silver boots, holding a red hardcover book in one hand. The storefront is filled with elegant illuminated typography and poster design. The main sign above the entrance clearly reads: “THE MIDNIGHT ARCHIVE” A large window poster clearly reads: “OPEN UNTIL 2 AM” A smaller promotional sign beside the door clearly reads: “RARE BOOKS • ART • DESIGN” The red book in her hand has the clearly legible title: “MEMORIES OF TOMORROW” Sophisticated editorial composition, cinematic blue and amber lighting, realistic glass reflections, clean typography hierarchy, premium graphic design, photorealistic fashion photography, highly detailed, all text perfectly spelled and clearly readable.

A cinematic product photo of an unbranded amber glass perfume bottle with a plain fros

A cinematic product photo of an unbranded amber glass perfume bottle with a plain frosted-glass label and no text or logo, on a marble surface, soft golden-hour lighting, shallow depth of field, elegant reflections, premium editorial photography style

A handsome young Mediterranean man standing on the rooftop of an old apartment buildin

A handsome young Mediterranean man standing on the rooftop of an old apartment building just before a storm, wearing a loose white shirt and dark trousers, struggling to pull a huge white bedsheet from a clothesline as powerful wind turns it into a sail around him, dramatic dark clouds approaching behind the city skyline, warm sunlight breaking through one gap in the clouds, poetic cinematic realism, expressive full-body action.

A cheerful young woman chef with rolled sleeves tossing fresh pasta in a steaming copp

A cheerful young woman chef with rolled sleeves tossing fresh pasta in a steaming copper pan in a rustic trattoria kitchen, flames leaping from the stove, flour dust glowing in warm light, candid cinematic food photography, shallow depth of field, no signs or text anywhere

A clean infographic poster titled "HOW A TREE DRINKS WATER" showing a large illustrate

A clean infographic poster titled "HOW A TREE DRINKS WATER" showing a large illustrated oak tree with a cross-section of roots, trunk and leaves, blue arrows tracing water flow, and four numbered labels: "1. Roots absorb", "2. Xylem carries", "3. Leaves release", "4. Clouds return rain", flat vector style, soft earthy palette

GPT Image 2.5 Flare API reference

Endpoints, request fields and runnable examples for this model.

Base URL

https://01router.com/api/v1

llms.txt

Quick start

Set API_KEY to your project key, then run a sample from your server. Replace example media URLs with your own public URLs.

Auto-routing chooses a provider that supports the request. Select a provider to see its input constraints and pinned request examples.

curl https://01router.com/api/v1/generations \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2.5-flare",
  "input": {
    "prompt": "A cinematic shot of a red fox running through snow",
    "aspect_ratio": "1:1",
    "quality": "medium",
    "num_images": 1
  }
}
JSON

# Replace GENERATION_ID with the id returned above; poll until status is "succeeded" or "failed"
curl https://01router.com/api/v1/generations/GENERATION_ID -H "Authorization: Bearer $API_KEY"

Endpoints

Only endpoints relevant to this model are listed. Paths below include /api/v1. Click an endpoint to read its usage.

POST

/api/v1/generations

Create a generation (charges credits) · API key required

GET

/api/v1/generations/{id}

Get a generation; polls the provider while running · API key required

POST

/api/v1/generations/{id}/cancel

Cancel a running generation (credits refunded) · API key required

POST

/api/v1/quote

Price a request on every provider (no charge, no key needed) · Public · no key

POST

/api/v1/images/generations

OpenAI-compatible image generation (waits for the result) · API key required

GET

/api/v1/models/gpt-image-2.5-flare

Get one model · Public · no key

Authentication

Send your API key as a Bearer token. Requests are billed to the key owner's credits.

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Get an API key

Input

Send JSON with Content-Type: application/json. Model parameters belong inside input; model, provider and callback_url are top-level fields.

Request body

Name	Type	Required	Description
model	string	Yes	"gpt-image-2.5-flare"
provider	string	No	Pin a provider; omit to auto-route to the cheapest. One of: fal \| 01router \| replicate \| wavespeed \| kie \| vercel
input	object	Yes	Model parameters, see the input fields below.
callback_url	string	No	Optional public HTTPS webhook URL. The final task result is signed and delivered here; polling remains available.

input · input fields

Required fields are marked explicitly. Other fields use the listed defaults when omitted.

Name	Type	Required	Values	Default
prompt*	string	Yes	—	—
image_urls Optional — switches to image editing	string[]	No	maxItems: 10	—
aspect_ratio	string	No	1:1 \| 4:3 \| 3:4 \| 16:9 \| 9:16 \| 3:2 \| 2:3	1:1
quality	string	No	low \| medium \| high \| xhigh \| max	medium
num_images	integer	No	min: 1 · max: 4	1

Callbacks →

Output

Creating a task does not mean generation has finished. Keep its id, poll until succeeded or failed, then read outputs or error. Amounts below are illustrative; actual charges depend on the request.

queued→processing→succeeded / failed

Task submitted

{
  "id": "gen_example",
  "object": "generation",
  "model": "gpt-image-2.5-flare",
  "type": "image",
  "provider": "fal",
  "status": "processing",
  "input": {
    "prompt": "A cinematic shot of a red fox running through snow",
    "aspect_ratio": "1:1",
    "quality": "medium",
    "num_images": 1
  },
  "outputs": [],
  "error": null,
  "credits": 0,
  "price_usd": 0,
  "created_at": "2026-10-25T08:00:00.000Z",
  "completed_at": null
}

Task completed

{
  "id": "gen_example",
  "object": "generation",
  "model": "gpt-image-2.5-flare",
  "type": "image",
  "provider": "fal",
  "status": "succeeded",
  "input": {
    "prompt": "A cinematic shot of a red fox running through snow",
    "aspect_ratio": "1:1",
    "quality": "medium",
    "num_images": 1
  },
  "outputs": [
    "https://example.com/output.png"
  ],
  "error": null,
  "credits": 0,
  "price_usd": 0,
  "created_at": "2026-10-25T08:00:00.000Z",
  "completed_at": "2026-10-25T08:01:00.000Z"
}

Response fields

Name	Type	Required	Description
id	string	Yes	Generation ID. Use it to query or cancel this task.
object	string	Yes	generation
model	string	Yes	gpt-image-2.5-flare
type	string	Yes	image
provider	string	Yes	Provider
status	string	Yes	queued → processing → succeeded / failed. Stop polling at either terminal state.
input	object	Yes	Model parameters, see the input fields below.
outputs	string[]	Yes	Result URLs. Empty while processing; read after succeeded and save the files promptly.
error	string \| null	Yes	Failure reason, or null when no failure is reported.
credits	number	Yes	Credits charged for this request.
price_usd	number	Yes	Request price in USD.
created_at	string	Yes	Creation time in ISO 8601 format.
completed_at	string \| null	Yes	Completion time in ISO 8601 format; null before completion.

Get the result

Poll every few seconds until status is succeeded or failed. Output URLs are provider-hosted and may expire — download them promptly. Or pass callback_url to get the result pushed.

curl "https://01router.com/api/v1/generations/GENERATION_ID" \
  -H "Authorization: Bearer $API_KEY"

queued → processing → succeeded / failed. Stop polling at either terminal state. Result URLs. Empty while processing; read after succeeded and save the files promptly.

Cancel a task

Cancellation depends on provider support and task state. A confirmed cancellation returns status: failed and error: Canceled by user. Unsupported or completed tasks return 409 not_cancelable.

curl -X POST "https://01router.com/api/v1/generations/GENERATION_ID/cancel" \
  -H "Authorization: Bearer $API_KEY"

Quote

Same body as creating a generation. Returns every available provider sorted by price, plus the ones that cannot serve the request and why.

curl "https://01router.com/api/v1/quote" -H "Content-Type: application/json" --data-binary @- <<'JSON'
{
  "model": "gpt-image-2.5-flare",
  "input": {
    "prompt": "A cinematic shot of a red fox running through snow",
    "aspect_ratio": "1:1",
    "quality": "medium",
    "num_images": 1
  }
}
JSON

OpenAI-compatible images

For OpenAI SDK integrations, use this endpoint with top-level prompt. It waits for the result and returns data[].url. For asynchronous tasks and the full model parameter set, use /generations.

curl "https://01router.com/api/v1/images/generations" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" --data-binary @- <<'JSON'
{
  "model": "gpt-image-2.5-flare",
  "prompt": "A cinematic shot of a red fox running through snow"
}
JSON

{
  "created": 1792915200,
  "data": [
    {
      "url": "https://example.com/output.png"
    }
  ]
}

Model schema

This public endpoint returns the model parameters and each provider’s supported constraints and prices.

curl "https://01router.com/api/v1/models/gpt-image-2.5-flare"

Errors

Check the HTTP status and error.message. Fix the request before retrying validation or authentication errors. A failed generation is reported in status and error on the task itself.

{
  "error": {
    "message": "Invalid or missing API key",
    "code": "unauthorized"
  }
}

400Invalid body or parameter value

401Missing or invalid API key

402Not enough credits

404Unknown model or generation

409The task cannot be canceled (already finished, or the provider does not support canceling)

429Too many requests — retry after the given seconds

502Every provider rejected the task (credits refunded)

Auth, routing, billing and error codes are covered in →

Use with AI

Give your coding assistant this model reference: endpoints, input constraints, output fields and request examples in plain text.

Open llms.txt

How does GPT Image 2.5 Flare compare?

Specs and starting prices side by side. Test with the same prompt before you choose.

	GPT Image 2.5 Flare	GPT Image 2.5 Sunburst	Nano Banana 2.1	Seedream 5.0 Pro
Vendor	OpenAI	OpenAI	Google	ByteDance
Starting price	$0.0053 / image	$0.0053 / image	$0.018 / image	$0.026 / image
Input	Text · Image	Text · Image	Text · Image	Text · Image
Provider	6 providers	6 providers	8 providers	6 providers
Aspect ratio	1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3	1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3	1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 4:5 · 5:4 · 21:9	1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9
Quality	low · medium · high · xhigh · max	low · medium · high · xhigh · max	—	—
Images	1 – 4	1 – 4	1 – 4	1 – 4

GPT Image 2.5 Flare API FAQ

What is GPT Image 2.5 Flare?

Flare is OpenAI's fast, balanced GPT Image 2.5 tier for everyday generation and editing: natural lighting, rich textures, complex layouts and reliable text, with lower latency than Sunburst.

Can I edit images or use references?

Yes. Add one or more images in image_urls to edit them or combine subjects and styles. Describe exactly what should change and what must stay the same.

Which quality level should I use?

low for quick drafts, medium for most work, high for marketing and text-heavy images, xhigh or max for print and the finest detail. Higher quality costs more and takes longer.

How do I get accurate text in images?

Put the exact wording in double quotes and describe the typography, such as font style, colour and placement. Use high quality for small or dense text.

How is it billed on 01router?

Per generated image, with the price depending on quality and provider; see the pricing table. num_images multiplies the cost. Failed generations are refunded.