Text-to-Image
V3 introduced major advances in photorealism and text rendering. It was the first Recraft model to generate mid-size text accurately and, as of 2025, is the only model capable of placing text at specific positions in an image.
1,072
Oct 2024
image
$0.04/img
Catalog
Category rows come directly from Artificial Analysis when the endpoint exposes category-level Elo scores.
| Category | Elo | 95% CI | Appearances |
|---|---|---|---|
| Nature & Landscapes | 1,127 | -27/27 | 780 |
| General & Photorealistic | 1,124 | -14/14 | 3,020 |
| General | 1,116 | -28/28 | 655 |
| Text & Typography | 1,116 | -40/40 | 347 |
| General | 1,115 | -13/13 | 3,078 |
| Vintage & Retro | 1,110 | -37/37 | 374 |
| General | 1,107 | -24/24 | 914 |
| General | 1,107 | -28/28 | 633 |
| People: Groups & Activities |
| 1,105 |
| -29/29 |
| 676 |
| Traditional Art | 1,101 | -35/35 | 422 |
| General | 1,094 | -29/29 | 581 |
| General | 1,093 | -11/11 | 4,353 |