# GPT Image Mini

> The lightweight GPT Image tier; generation is paused until an exact verified route is available.

Canonical URL: https://allimageai.com/models/gpt-image-mini/

Website: All Image AI

Language: English

The lightweight GPT Image tier. It keeps the instruction-following advantage, caps output at 1K, and exists for fast iteration.

## Model details

- Developer: OpenAI
- Status on All Image AI: Temporarily Unavailable
- Last verified: 2026-08-20
- Maximum output: 1K
- Modes: Text to Image, Image to Image, Edit Image
- Reference images: up to 2
- Resolutions: 1K
- Aspect ratios: 1:1, 3:2, 2:3

## Best for

- Drafts and composition exploration
- Batch generation followed by manual selection

## How to use

1. Select GPT Image Mini
2. Batch generate and pick a composition
3. Use as Reference on the standard tier to finish

## Settings explained

### Number of Images

Leave it at 4 — parallel drafting is the point of this tier.

## Prompt examples

### Fast draft

> Three layout options for a podcast cover, bold type, dark background

## Limitations

- Generation is temporarily unavailable
- 1K output only
- No substitute model is used silently

## Pricing and credits

Credits for one image at default quality and mode. Resolution, quality, reference inputs, edit mode and output count can change the total. Check the Generate button before submitting.

| Resolution | Credits / image |
| --- | --- |
| 1K | 1 |

Failed generations cost 0 credits. Catalog availability does not guarantee runtime availability; the workspace reports whether the selected model can run.

[Credit plans](https://allimageai.com/pricing.md)

## Test results

Testing in progress. No verified benchmark scores have been published for this model.

## Commercial use and image handling

You own the output; use is subject to OpenAI's usage policies.

Uploads are processed by the configured inference service. You can delete a generation from your history.

## Frequently asked questions

### How much quality do I give up versus the standard tier?

Composition and instruction following are close. The gap is resolution ceiling and detail density.

## Release history and sources

Date not yet established.

The catalog route identifies gpt-image-1-mini, but the supplied audit still requires confirmation of the historical model mapping. Its candidate date stays outside the dated timeline.

- [developers.openai.com](https://developers.openai.com/api/docs/changelog)

[Event evidence on the timeline](https://allimageai.com/timeline/#event-gpt-image-mini)

## Other versions

- [GPT Image 2.5 Flare](https://allimageai.com/models/gpt-image-2-5-flare.md): Fast generation · Up to 4K
- [GPT Image 2.5 Sunburst](https://allimageai.com/models/gpt-image-2-5-sunburst.md): Detailed edits · Reference fidelity
- [GPT Image](https://allimageai.com/models/gpt-image.md): Recommended · 4K
- [GPT Image 1.5](https://allimageai.com/models/gpt-image-1-5.md): Quality tiers · 1K