Sber's flagship large-scale Mixture-of-Experts model with 702B total parameters and 36B active. Designed for multilingual assistant workloads, reasoning, code generation, tool use, and large-cluster deployment. Open-weight release.
32K tokens
1
available
Cheapest
Sber
$14.00/1M tokens
Sber
Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.
| Provider | Pricing (per 1M) | Rate Limits | Regions | Health | Latency |
|---|---|---|---|---|---|
In: $3.50Out: $10.50 | 50 RPM / 100K TPM | ru-central-1 | Unhealthy | 0ms |
Use this model via Sber with an OpenAI-compatible SDK.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.sber.com/v1",
apiKey: process.env.SBER_API_KEY,
});
const response = await client.chat.completions.create({
model: "GigaChat-Ultra",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);Using Sber API • OpenAI-compatible SDK