Text-to-Image
GPT Image 1 is OpenAI's new state-of-the-art image generation model. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.
1,126
Apr 2026
image
$5/1M
Catalog
Category rows come directly from Artificial Analysis when the endpoint exposes category-level Elo scores.
| Category | Elo | 95% CI | Appearances |
|---|---|---|---|
| Traditional Art | 1,263 | -41/41 | 217 |
| Fantasy & Mythical | 1,221 | -27/27 | 400 |
| General | 1,172 | -28/28 | 445 |
| General | 1,171 | -21/21 | 793 |
| General | 1,165 | -15/15 | 1,352 |
| Vintage & Retro | 1,165 | -40/40 | 281 |
| General | 1,164 | -16/16 | 1,220 |
| General | 1,162 | -20/20 | 788 |
| People: Portraits |
| 1,156 |
| -33/33 |
| 313 |
| General | 1,147 | -12/12 | 1,976 |
| General & Photorealistic | 1,142 | -16/16 | 891 |
| General | 1,142 | -13/13 | 1,881 |