Kandinsky-3.1 is a large text-to-image diffusion model developed by Sber and AIRI, featuring 11.9 billion parameters. The model consists of a text encoder, U-Net, and decoder, enabling high-quality, detailed image generation from text prompts. It is trained on extensive datasets and is designed for both creative and scientific applications.
Retired on Aug 22, 2026: requests to this model ID now return an error. These models are live and work with the same API key.
Kandinsky-3.1 is a large text-to-image diffusion model developed by Sber and AIRI, featuring 11.9 billion parameters. The model consists of a text encoder, U-Net, and decoder, enabling high-quality, detailed image generation from text prompts.
No. Kandinsky 3.1 was retired on NagaAI on Aug 22, 2026, and requests to it now return an error. Live models you can use instead with the same API key: GPT Image 2.6 Sunburst, GPT Image 2.6 Flare and Riverflow V2.6 Pro.
It takes text as input and returns images.
