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.
1,125
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 | 1,220 | -38/38 | 281 |
| Fantasy & Mythical | 1,214 | -26/26 | 521 |
| General | 1,171 | -26/26 | 590 |
| General | 1,170 | -19/19 | 1,061 |
| General | 1,168 | -15/15 | 1,803 |
| General | 1,165 | -20/20 | 1,018 |
| General | 1,164 | -38/38 | 301 |
| Vintage & Retro | 1,160 | -36/36 | 381 |
| General |
| 1,155 |
| -15/15 |
| 1,611 |
| People: Portraits | 1,145 | -31/31 | 417 |
| People: Groups & Activities | 1,144 | -32/32 | 330 |
| General | 1,143 | -12/12 | 2,586 |