See how Recraft-ai's models evolved by answering the same challenge across generations.
Provider of advanced AI models and technologies.
6
Oct 2024 – Feb 2026
Recraft V4 is a ground-up rebuild of Recraft's image generation with built-in design taste — the model makes intentional decisions about composition, lighting, color, and material realism. Supports prompts up to 10,000 characters with accurate text rendering.
Recraft V4 Pro generates high-resolution images at ~2048px (scalable to 3072px) with the same design taste as V4. Optimized for print production, large-format displays, and detailed professional work requiring maximum quality.
Recraft V4 SVG generates production-ready SVG vector images from text prompts with real paths, structured layers, and clean geometry. The only image model that produces native, editable vector output.
Recraft V4 Pro SVG combines V4 Pro's design taste with detailed geometric vector output. Produces detailed SVG files with finer paths, clean layers, and editable output suitable for professional design systems.
Recraft V3 (code-named red_panda) is a SOTA text-to-image model ranked #1 on Artificial Analysis benchmarks. The first model to offer image generation with text of any size and length, supporting both raster and vector output formats across a wide list of styles.
Recraft V3 SVG generates high-quality vector SVG images from text prompts, including logotypes, icons, and illustrations. Produces real editable SVG files with clean paths and structured layers.
