Skip to main content

Filtered — This model refuses requests beyond its own limits outright. Measured, not assumed — models we have not measured carry no label at all.Browse every model at this filtering level
openai/gpt-image-2.5-flare/text-to-image

OpenAI's GPT Image 2.5 Flare text-to-image, the speed-first model of the GPT Image 2.5 pair. Choose five quality tiers from low to max, 1K, 2K or 4K output and 15 aspect ratios from 1:3 to 3:1, as PNG, JPEG or WebP.

From $0.0018/image20% below the publisher's list price
Run model

Workbench

Input

Text to image
233/5000
Up to 5,000 characters. Put every word that must appear in the image in double quotes and say where it goes; the rest is read as description. The first 100 input tokens of the prompt are included in the image price; longer prompts add a small charge per extra token, shown in the quote. Chinese, Japanese and Korean text counts about one token per character, other text about one token per four characters. at least 1 characters · at most 5000 characters
affects price
Fifteen shapes from 1:3 to 3:1, 1:1 by default. The shape changes the price: a wide or tall frame costs less than a square at the same tier.
affects price
1k (default), 2k or 4k. A square frame is 1024, 2048 or 2880 pixels across; a larger tier costs more per image. On the economy route a 1k image can come out somewhat larger.
Qualityaffects price
lowmediumhighxhighmax
low, medium, high (default), xhigh or max. Each step adds detail, time and cost; keep xhigh and max for finals.
Output format
PNGJPEGWebP
png (default), jpeg or webp. Does not change the price.
Output quality
Compression quality for jpeg and webp, 0 to 100: higher keeps more detail and makes larger files. Not used for png, and it does not change the price. no lower than 0 · no higher than 100
Official fallback
On by default. A request for a single high-quality 1k PNG in 1:1, 3:2, 2:3, 4:3, 3:4, 16:9 or 9:16 runs on the economy route first; if that route cannot complete it, for example because it refuses the prompt, the request runs again on the official route and is billed at the official price instead of the economy price. Every other request runs on the official route from the start. Turn it off to pay only the economy price: requests the economy route cannot serve are then rejected, and one it takes may still be refused or fail.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
terrace-dressExample result
Animate
Edit
Split into layers

Missing the model you need?

Tell us what to add and where you would use it. Requests go to the people who decide what gets onboarded next.

OPENAI IMAGE API

GPT Image 2.5 Flare API at a glance

OpenAI's fastest image model, GPT Image 2.5 Flare, with every control; high-quality 1K images start well below OpenAI's list price.

Economy route
1K
High-quality 1K images in seven common shapes start on a lower-priced route; Official fallback reruns anything it cannot finish on the official route.
OpenAI image model
Fastest
OpenAI calls Flare its fastest model for everyday generation.
Edit sources
16
Up to sixteen source images plus a mask in one edit.
Images per request
10
Up to ten variations of one prompt in a single call.

Results

What you can make with GPT Image 2.5 Flare

  • A man in a charcoal overcoat and open white shirt in the doorway of a small ramen bar on a rainy night, a red neon sign reading OPEN LATE beside him

    Speed

    A finished frame in about half a minute

    A man in a charcoal overcoat in a ramen-bar doorway on a rainy night, beside a legible red neon sign reading OPEN LATE. High quality at 16:9, returned in under 30 seconds.

    Text to image, high quality, 16:9.

  • The man in the overcoat and the woman in a light trench coat standing close in the ramen-bar doorway in the rain

    Multi-image

    Two sources, one scene

    The man from the ramen bar and the woman from the terrace, placed together in the rainy doorway, each face kept from its own source.

    Edit, two sources, 16:9.

  • The same woman on the terrace in a red one-shoulder satin dress at blue hour, village lights coming on

    Editing

    Wardrobe and time of day in one pass

    The white sundress became a red one-shoulder satin dress and the sunset turned to blue hour, while her face, her hair and the terrace stayed the same.

    Edit, one source, 4:5.

Content test

Is GPT Image 2.5 Flare uncensored? What we tested

We ran each level on our live setup and checked every clip frame by frame. A pass means the content was actually on screen, not just that the request went through.

Content levels tested on GPT Image 2.5 Flare, by mode
LevelImage editingText to image
MildThe lightest prompts in the test
RefusedTested Sep 29, 2026
RefusedTested Sep 29, 2026
ModerateWhere filtered models start to refuse
Not tested yet
Not tested yet
StrongThe middle of the scale
RefusedTested Sep 29, 2026
RefusedTested Sep 29, 2026
Very strongWhere most models start to hold back
Not tested yet
Not tested yet
MaximumThe top of the scale
Not tested yet
Not tested yet

Renders: on screen as written. Softened: generated, but milder than what was written. Refused: rejected. Not tested yet: we have not run that level on that mode.

How each mode behaves

All modes
OpenAI's safety system screens every prompt and result. In our tests every request from the Mild level up was refused at every quality tier, and one ordinary neon street poster was refused as well. Refused requests are not charged.

Use cases

What to build with the GPT Image 2.5 Flare API

  • Social and feed content

    Daily posts, story frames and ad variations where many good images per hour matter more than the last bit of detail.

  • Previews and interactive tools

    Apps that show an image while the user waits, and design tools that generate options as someone types.

  • Quick composites

    Two people from separate shots in one scene, or one person moved to a new place, with faces kept from their sources.

Prompts

GPT Image 2.5 Flare prompt examples you can copy

Paste one into the playground as it is, then change one thing at a time.

  • Text to image

    A finished frame in about half a minute

    A man in a charcoal overcoat and an unbuttoned white shirt stands in the doorway of a tiny ramen bar on a rainy street at night, steam drifting past a red neon sign that reads "OPEN LATE", reflections on the wet asphalt, he glances back at the camera.

    Why it works. High quality at 16:9 with the sign text quoted. The request returned in under 30 seconds, which is the reason to pick Flare for volume work.

    Try this prompt

  • Image editing

    Two sources, one scene

    Use the man from Image 1 and the woman from Image 2. Put them together in the doorway of the ramen bar from Image 1 on the same rainy night: she stands close under his open coat to keep out of the rain, both looking at the camera. Keep both faces as they are; she now wears a light trench coat over her dress.

    Why it works. Two sources: the man and the setting come from the first image, the woman from the second. The prompt gives her a new coat so both outfits suit the rain.

    This mode starts from your own image: add it in the playground before you run.

    Try this prompt

  • Image editing

    Wardrobe and time of day in one pass

    Change her white sundress to a red one-shoulder satin dress and turn the sunset into blue hour with the first lights of the village coming on. Keep her face, hair, pose and the terrace exactly as they are.

    Why it works. One source. Two changes in one prompt (the dress and the time of day), then a short list of what stays: face, hair, pose and terrace.

    This mode starts from your own image: add it in the playground before you run.

    Try this prompt

Pricing

GPT Image 2.5 Flare API pricing

One image starts at $0.0018 at 1K and $0.0037 at 4K.

The playground shows the exact price for your settings before you run. Failed or timed-out tasks are usually not charged. Some models charge for content refusals as stated on their model page; check those billing terms before submitting.

See every price tier

Get started

How to use the GPT Image 2.5 Flare API in three steps

  1. Step 1

    Use it for volume

    Flare costs the same per token as Sunburst, so the reason to pick it is turnaround: batches, previews and interactive tools. In our runs most high-tier 1k images finished in 25 to 45 seconds.

  2. Step 2

    Keep high as the default

    High is where Flare produces finished-looking images; drop to low or medium only for rough previews, and use max for the handful of frames that go to print.

  3. Step 3

    Combine sources by order

    In edits, call the sources the first image, the second image and so on, and say what each one contributes to the new frame.

Open the playgroundGet an API key

Parameter reference and code samples are in the API and Readme tabs at the top of this page.

Why SpicyAPI

Why run GPT Image 2.5 Flare on SpicyAPI

  • No filter from us

    We add no content filter of our own. What the model renders is what you get back.

  • Tested, not guessed

    Content labels come from real generations we ran and checked, with the test date on the page.

  • Pay per result, in dollars

    No subscription and no credits. Failed or timed-out tasks are usually not charged. Some models charge for content refusals as stated on their model page; check those billing terms before submitting.

  • One key for every model

    One API key and balance cover image, video, audio and chat models, so you can explore more models from the same account.

FAQ

GPT Image 2.5 Flare API FAQ

About GPT Image 2.5 Flare

GPT Image 2.5 Flare is OpenAI's fastest image model: the same five quality tiers, transparent cut-outs and sixteen-source editing as Sunburst, fifteen aspect ratios from 1K to 4K, and every setting priced below OpenAI's list price. OpenAI’s content policy applies, so it suits high-volume design and social work rather than work past the Mild level.

All GPT Image models3

Related models and next tasks