GPT Image 1.5 AI Image Generator

Developer

OpenAI

Model

GPT Image 1.5

Status

Active

Max Output

Input

Text

Released

December 16, 2025

Last Verified

August 25, 2026

What Is GPT Image 1.5?

GPT Image 1.5 is OpenAI’s high-fidelity image generation model for prompts that specify composition, lighting, exact copy and several interacting constraints. Low, Medium and High are separate visible billing tiers, and transparent output can be requested directly.

GPT Image Model Versions

GPT Image

Recommended · 4K

From 5 Credits

Open this version →

GPT Image 1.5

Quality tiers · 1K

From 4 Credits

GPT Image Mini

Fastest · 1K

From 1 Credits

GPT Image

Treats a complex brief as a task to execute, not a bag of keywords to match.

Resolutions: 1K / 2K / 4K
Reference images: up to 4
Modes: Text to Image, Image to Image, Edit Image, Multi-reference
Speed: Balanced

GPT Image 1.5

OpenAI’s high-fidelity image generation model for precise composition, lighting, detail and readable text.

Resolutions: 1K
Reference images: not supported
Modes: Text to Image, Typography
Speed: Balanced

GPT Image Mini

The same instruction following at a draft price point.

Resolutions: 1K
Reference images: up to 2
Modes: Text to Image, Image to Image, Edit Image
Speed: Fastest

What Is GPT Image 1.5 Best For?

Long instruction-rich briefs
Readable display text
Transparent creative assets
Precise composition and lighting

How to Use GPT Image 1.5

Write the brief as clear sentences.
Quote every required word.
Draft at Low or Medium.
Use High only for the selected final.

GPT Image 1.5 Settings Explained

Quality

Low is for composition drafts, Medium is the balanced default, and High spends much more for final detail.

Background

Transparent requests an alpha channel; Opaque guarantees a filled canvas.

The panel above shows only the parameters GPT Image 1.5 actually supports. Switch versions and unsupported controls disappear rather than sitting there doing nothing.

GPT Image 1.5 Prompt Examples

Historical scene

Realistic handheld phone photograph from the deck of an early twentieth-century ocean liner at night, cold mist, period-correct clothing, physically plausible lighting

Transparent mark

Playful enamel camping badge reading “NORTH / 27”, crisp lettering, pine and moon motif, isolated with a transparent background

GPT Image 1.5 Test Results

Testing in progress

Every model runs the same eight-category prompt set — portrait, product, poster text, anime character, interior, multi-reference, image editing and character consistency — recording generation time, success rate, text accuracy and identity retention. That run has not finished for GPT Image 1.5, so this page shows no scores. We do not publish numbers we have not measured.

GPT Image 1.5 Limitations

Token usage makes the exact upstream cost variable
High quality is substantially more expensive
This page exposes generation, not image editing

GPT Image 1.5 Pricing and Credits

Credits scale with resolution and image count. The Generate button always shows what this run costs.

4 credits / image

Failed generations cost 0 credits.

Commercial Use and Image Rights

You own the output; use remains subject to OpenAI usage policies and the selected service terms.

Model used: GPT Image 1.5
Model developer: OpenAI
The inference route is managed internally and may change without changing the selected model
Uploads are sent only to the configured inference service needed to complete the generation
You can delete any generation from your history at any time