Kandinsky 3.1
Review Kandinsky 3.1 on key metrics including price, context length, throughput, and model features.
AuthorSberBank
Context Length-
Supports Tools
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.
Activity
Last 14 daysNot enough activity yet
Prompt
0Completion
0Total
-Startup
Startup
Latency (p50)-
Throughput (p50)-
Pricing
Image$0.005/image
Features
Input Modalitiestext
Output Modalitiesimage
Supported EndpointsImage Generation
Vision
Supports Tools