Kandinsky 3.1

Image Generation

kandinsky-3.1

SberBank|Created May 31, 2025

Image Generation

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.

Overview Specifications Activity Performance Uptime Examples

Pricing-50%

Pay-as-you-go rates for this model. More details can be found here.

Image

$0.005

Capabilities

Input Modalities

Text

Output Modalities

Image

Supported Parameters

Available parameters for API requests

Size

Usage Analytics

Token usage of this model on our platform

Throughput

Not enough throughput data

Time-To-First-Token (TTFT)

Not enough TTFT data

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key="YOUR_API_KEY")

resp = client.images.generate(
    model="kandinsky-3.1",
    prompt="A white siamese cat",
    size="1024x1024",
    n=1,
    response_format="url",
)
print(resp.data)