Skip to main content

OpenAI's GPT Image 2.5 Flare image editing takes 1 to 16 source images and a text description of the change. Supply 1 to 16 references for a Flare composite, describe their roles in upload order, and allow for an input charge per source on each output when standard pricing applies.

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

Workbench

Input

Image editing
309/5000

Reordering updates prompt references. Removing media also removes its references; review your prompt.

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 price2/16

Drop files or media links, paste, or browse · Up to 16 files · Max 10 MB · JPG · PNG · WEBP · GIF

  • Image 1
  • Image 2
2 / 16 files
Supply 1 to 16 references for a Flare composite, describe their roles in upload order, and allow for an input charge per source on each output when standard pricing applies. at least 1 items · at most 16 items
affects price
Frame the Flare preview for its placement: 15 ratios span 1:3 to 3:1, with 1:1 as default and a separate price for each shape.
affects price
Flare previews start at 1k; 2k and 4k increase the image price, with square outputs measuring 1024, 2048 and 2880 pixels respectively.
Qualityaffects price
lowmediumhighxhighmax
For quick finished frames, Flare defaults to high; low and medium suit drafts, while xhigh and max spend more time and money on detail.
Official fallback
GPT Image 2.5 Flare is billed per output by quality, resolution and shape; standard-priced edits add a fixed source-image charge to each output, and wide or tall shapes cost less than squares at the same tier. The lower-priced GPT Image 2.5 Flare offer covers one high 1k PNG, in 1:1, 3:2, 2:3, 4:3, 3:4, 16:9 or 9:16, and for edits only with no mask, input_fidelity low and background auto. With Official fallback enabled by default, a lower-priced request that is refused or cannot finish is retried at the standard price; the GPT Image 2.5 Flare quote shows the starting amount and maximum, other settings use standard pricing immediately, and disabling fallback rejects settings outside the offer without guaranteeing success for eligible ones. A refused GPT Image 2.5 Flare request is not charged; under standard pricing only, prompt tokens after the first 100 add a fee once per request, estimated at one token per Chinese, Japanese or Korean character and about one per four other characters.
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
two-refs-neonExample result

Missing the model you need?

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.

Starting offer
1K
The lower-priced GPT Image 2.5 Flare offer covers one high 1k PNG, in 1:1, 3:2, 2:3, 4:3, 3:4, 16:9 or 9:16.
OpenAI image model
Fastest
OpenAI calls Flare its fastest model for everyday generation.
Edit sources
16
Supply 1 to 16 references for a Flare composite, describe their roles in upload order, and allow for an input charge per source on each output when standard pricing applies.
Images per request
10
Flare returns 1 image unless you request more, up to 10; budget for each variation separately.

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

Content levels tested on GPT Image 2.5 Flare, by mode
LevelImage editingText to image
Mild
RefusedTested Sep 29, 2026
RefusedTested Sep 29, 2026
Moderate
Not tested yet
Not tested yet
Strong
RefusedTested Sep 29, 2026
RefusedTested Sep 29, 2026
Very strong
Not tested yet
Not tested yet
Maximum
Not tested yet
Not tested yet
How we test

How each mode behaves

All modes
Flare is filtered: OpenAI checks prompts and generated images, and SpicyAPI’s existing tests refused every tested request from Mild upward, including one ordinary neon poster. Rejected Flare jobs cost nothing; SpicyAPI adds no filter and cannot remove OpenAI’s checks, so consult catalogue families marked unrestricted for a different policy.

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

  • 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.

    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.

    Try this prompt

Pricing

GPT Image 2.5 Flare API pricing

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

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.

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

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.

Related models and next tasks