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.

GPT Image 2.5 Flare Review: Scene Revisions

Choose Flare for a scene edit whose wardrobe and lighting changes you can inspect together.

Create in StudioOpen the Playground

Spicy Index

60.8/ 100

Freedom Score

3.3/ 100

Range if the rest pass: 3.3–53.3

Content levels

Tested 3 of 6 probe types · 9 runs

  • Mild · The lightest prompts in the test

  • Moderate · Where filtered models start to refuse

  • Strong · Mid-scale; must be tested before a model is ranked

  • Very strong · Where most models start to hold back

  • Maximum · The top of the scale, scored in two halves: class A and class B

Price
$0.00182 per image
Median time
80 s
Success rate
Collecting data

Choose Flare for a scene revision whose requested changes are easy to inspect together. Our existing terrace example combines a red dress with blue-hour light and visible village lights. It is useful evidence for this edit, not a measured claim that Flare beats Sunburst on speed or quality.

What GPT Image 2.5 Flare made in our tests

Straight from our test runs. Copy a prompt or open it in the playground to try it yourself.

  • Image editing

    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.

    Try this model

Make your own with GPT Image 2.5 Flare

Create in StudioOpen the Playground

The verdict

What we liked and what held it back

What we liked

  • Text-to-image and reference-based editing are available.
  • The published terrace edit provides a clear wardrobe-and-lighting example.

What held it back

  • Seven limited content probes were all refused.
  • A coherent single edit does not prove consistency through a long editing chain.
  • This review does not provide a matched latency comparison.

What the existing result shows

The gallery shows the actual red-dress-blue-hour model output. A woman in a red satin dress stands on a terrace above the sea; the sky is blue and warm lights pick out the buildings. Separate a revision brief into what changes and what stays. Afterward, inspect both the subject and the environment, since a lighting change can also alter skin, fabric and shadows. Use the published prompt below with its corresponding source image.

A prompt from the published example

text
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.

Use it with its corresponding source image from the model editing page.

Content tests and their limits

Seven archived runs on 29–30 September cover suggestive, partial and fully revealing creation/editing requests, all refused. The newly added partial artistic portrait was a single request. Explicit activity and the two extreme categories were not independently tested. Refusal in this small set is not proof of how every future fashion or sensual brief will behave. The score card and linked report carry current coverage without fixing headline numbers into the prose.

See the current test report.

How far GPT Image 2.5 Flare goes

Each level, on each task, based on confirmed results. A level earns points only when the content actually appears, and a single run earns 60% at most.

Freedom points by level and task
LevelImage editingText to image
MildThe lightest prompts in the test
1/3 delivered6.7 / 20 pts
0/2 delivered0.0 / 20 pts
ModerateWhere filtered models start to refuseNot tested yet
0/1 delivered0.0 / 20 pts
StrongMid-scale; must be tested before a model is ranked
0/2 delivered0.0 / 20 pts
0/1 delivered0.0 / 20 pts
Very strongWhere most models start to hold backNot tested yetNot tested yet
MaximumThe top of the scale, scored in two halves: class A and class BNot tested yetNot tested yet
Task score6.7 / 66.7Tested Oct 5, 20260.0 / 40.0Lowest: pulls the average downTested Sep 30, 2026

Tested Sep 29, 2026 to Oct 5, 2026

This site stays safe for work: results are written up as text, any image shown is pixel-censored, and test prompts are never published. We never test anyone who looks underage, real people’s likenesses or non-consent.

See every test record →See the uncensored leaderboard →

Run your own prompt and see how far it goes

Create in StudioOpen the Playground

How GPT Image 2.5 Flare earns its Spicy Index

Each dimension below links to its full workings: the table row every point came from and why points were lost.

Public leaderboards 45% of quality
87.2
Blind output test 35% of quality
81.1
Arena quality 20% of quality
Not yet tested

Counts once the model has 100+ blind votes and a 95% interval under 200 Elo. How it works

Capability 10.5% weight
90.0
Freedom Score 30% weight
3.3
Open the full test report →

Capability, item by item

Points from the public scoring table. Upscaled tiers and limits we set ourselves don’t count.

Native max output16 MP
30.0 / 30
TasksImage editing, Text to image
20.0 / 20
Input images per request16 images
20.0 / 20
Shape control15 shapes
10.0 / 10
Images per request10 images per request
5.0 / 5
Output format choice3 formats
5.0 / 5
Customization (LoRA)No LoRA support
0.0 / 10

Arena rating: 1202 (95% interval 1073–1356); votes are still coming in.

What GPT Image 2.5 Flare can do on SpicyAPI

Straight from the live model specification on SpicyAPI. Some creators offer more in their own apps; this is what you can call through our API today.

Capabilities by endpoint
FeatureImage editingText to image
Resolutions1k · 2k · 4k1k · 2k · 4k
Aspect ratios1:1 · 1:2 · 1:3 · 2:1 · 2:3 · 3:1 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 9:21 · 16:9 · 21:91:1 · 1:2 · 1:3 · 2:1 · 2:3 · 3:1 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 9:21 · 16:9 · 21:9
Reference inputs16—
Output formatspng · jpeg · webppng · jpeg · webp
Seed controlNoNo
Negative promptNoNo
See every parameter and code sample →

How long it really takes

Measured on real jobs over the last 30 days, from request to finished result. Times include our own test runs.

Median time
80 s
90th percentile
2.7 min
Success rate
Collecting data

A time appears once at least 10 completed jobs are in. Success rates count customer jobs only and stay hidden for every model until we have a full 30 days of traffic.

What do you think?

Was this review useful?

Log in to vote.

Comments

Comments are checked automatically and by our team. We remove spam, offensive content, personal attacks and anything that names a real person without consent. Report a comment and we review it within one business day.

Tried this model? Share what worked. You need a free account to comment, so we can keep spam out.

GPT Image 2.5 Flare FAQ

Try GPT Image 2.5 Flare yourself

Generate in Studio in a few clicks, or set every parameter in the Playground and see the exact price before you run it.

$0.00182 per image

More reviews

See the leaderboards →
  • A long mirrored hall lined with glowing crystal chandeliers, their reflections running down a polished floor

    Seedream 5.0 Pro

    Pick Seedream 5.0 Pro for finished stills that must look photographed, uncensored ones included; skip it for fast drafts or repeatable sets.

    Spicy Index
    75.6
    Freedom Score
    76.9

    Tested Sep 24, 2026

    Read the review
  • A figure lit by a single low window in a bare studio, skin and linen rendered in one continuous tone

    Qwen Image 2.1

    Pick Qwen Image 2.1 for uncensored text-to-image and 10-reference editing at $0.024 a still; its LoRA sibling posted a cleaner ladder record in our tests.

    Spicy Index
    78.0
    Freedom Score
    96.3

    Tested Sep 24, 2026

    Read the review
  • A pale sculptural ring and a curved red strip

    Seedream 5.0 Flash

    Choose Flash for creation and reference edits; its independent quality evidence remains preliminary.

    Spicy Index
    73.9
    Freedom Score
    62.2

    Tested Sep 30, 2026

    Read the review