GPT-Image 2 — Facts & Specifications
GPT-Image 2 is an AI image model available on Piooy. It supports text-to-image and image-to-image with 1K, 2K, 4K output. Published by OpenAI. Recently launched.
At a glance
- Model ID
- gpt-image-2
- Type
- AI image generation model
- Provider
- OpenAI
- Supported scenes
- text-to-image, image-to-image
- Aspect ratios
- auto, 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 2:1, 1:2, 21:9, 9:21
- Resolutions
- 1K, 2K, 4K
- Max prompt length
- 3,000 characters
- Max reference images
- 16
Capabilities
- Batch generation (up to 4 images per call)
- Up to 16 reference images
Pricing
Costs are denominated in Piooy credits. Credits can be purchased on the pricing page.
| Generation | Credits |
|---|---|
| text-to-image @ 1K | 5 |
| image-to-image @ 1K | 8 |
| text-to-image @ 2K | 8 |
| image-to-image @ 2K | 10 |
| text-to-image @ 4K | 10 |
| image-to-image @ 4K | 12 |
How to use GPT-Image 2
- Open the GPT-Image 2 generator — no signup is required.
- Enter a prompt (up to 3,000 characters), then choose your aspect ratio and resolution.
- Click Generate. The result downloads without a watermark.
Programmatic access is available via the Piooy API and the Piooy MCP server. The model id to pass to /api/v1/generate is gpt-image-2.