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.
1,073
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 | 1,128 | -27/27 | 767 |
| General & Photorealistic | 1,122 | -14/14 | 2,932 |
| General | 1,115 | -29/29 | 593 |
| General | 1,114 | -25/25 | 870 |
| General | 1,113 | -30/30 | 598 |
| General | 1,113 | -14/14 | 2,981 |
| Traditional Art | 1,107 | -36/36 | 405 |
| People: Groups & Activities | 1,107 | -29/29 | 664 |
| Vintage & Retro |
| 1,104 |
| -39/39 |
| 338 |
| Text & Typography | 1,100 | -39/39 | 339 |
| Commercial | 1,097 | -35/35 | 434 |
| General | 1,093 | -11/11 | 4,185 |