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 Review: Text and Targeted Edits

Choose GPT Image 2 for readable image text and narrowly specified revisions.

Open the Playground

Spicy Index

61.0/ 100

Freedom Score

10.0/ 100

Range if the rest pass: 10.0–45.0

Content levels

Tested 4 of 6 probe types · 12 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
85 s
Success rate
Collecting data

Choose GPT Image 2 for a picture that needs readable words and a specific revision brief. Our existing magazine-cover edit shows why: the requested masthead and two cover lines are legible, with a navy shirt, warm harbor light and the portrait still recognizable. This is one demonstrated edit, not a guarantee of identical pixels across revisions.

What GPT Image 2 made in our tests

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

  • Image editing

    Retype this magazine cover. Change the masthead to read "SALT & LINEN" in the same tall serif, and change the two cover lines to "NEW SEASON" and "THE ISLAND EDIT" in the same small bold sans-serif. Change his white linen shirt to a washed navy linen shirt. Keep his face, pose, the boat, the sea and the golden light exactly as they are.

    Try this model

Make your own with GPT Image 2

Open the Playground

The verdict

What we liked and what held it back

What we liked

  • Text and image editing are both available, including an optional mask for edits.
  • The published cover provides a concrete example of changing type and clothing in one request.

What held it back

  • Content limits remain even though SpicyAPI adds no safety checker.
  • Larger sizes and higher quality affect the quote; check it before each run.
  • We have not tested every layout, language or content category.

What the existing result shows

The gallery shows the actual retype-harbour model output. It reads SALT & LINEN, NEW SEASON and THE ISLAND EDIT. The subject wears a navy shirt beside the water. For a practical edit, name the words to replace, their positions and the details to retain. Inspect faces and background edges after the change rather than assuming nothing else moved.

A prompt from the published example

text
Retype this magazine cover. Change the masthead to read "SALT & LINEN" in the same tall serif, and change the two cover lines to "NEW SEASON" and "THE ISLAND EDIT" in the same small bold sans-serif. Change his white linen shirt to a washed navy linen shirt. Keep his face, pose, the boat, the sea and the golden light 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 strong probes across creation and editing. Six were refused; one suggestive edit rendered. The single new partial artistic-portrait probe was refused. Explicit activity and the two extreme categories were not independently tested here. Those outcomes describe these requests and this setup; they do not mean every sensual portrait is refused. The current score and per-run evidence belong in the test report, not a fixed number in this article.

See the current test report.

How far GPT Image 2 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
1/2 delivered8.0 / 20 pts
0/2 delivered0.0 / 20 pts
ModerateWhere filtered models start to refuse
1/1 delivered12.0 / 20 pts
0/1 delivered0.0 / 20 pts
StrongMid-scale; must be tested before a model is ranked
0/4 delivered0.0 / 20 pts
0/1 delivered0.0 / 20 pts
Very strongWhere most models start to hold back
0/1 delivered0.0 / 20 pts
Not tested yet
MaximumThe top of the scale, scored in two halves: class A and class BNot tested yetNot tested yet
Task score20.0 / 50.0Tested 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

Open the Playground

How GPT Image 2 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
81.7
Blind output test 35% of quality
81.2
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
10.0
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 request10 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: 1144 (95% interval 1017–1269); votes are still coming in.

What GPT Image 2 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 ratiosauto · 1:1 · 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 inputs10—
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
85 s
90th percentile
3.7 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 FAQ

Try GPT Image 2 yourself

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