Mistral AI

Mistral Nemo

A compact, fast Mistral

Text

Tools

Type: Chat
Context: 131K tokens
Russian: high
Input price: 1,52 ₽ / 1M tokens
Output price: 2,4 ₽ / 1M tokens
Release date: July 2024

chat/completions

import OpenAI from "openai"
const client = new OpenAI({
  baseURL: "https://api.yenisei.ru/v1",
  apiKey: process.env.YENISEI_API_KEY,
})
const stream = await client.chat.completions.create({
  model: "mistral-nemo",
  messages: [{ role: "user", content: "Hi!" }],
  stream: true,
})
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

About the model

Mistral Nemo is a small, fast Mistral model for standard conversational tasks with low latency and cost. It answers quickly in chats and auto-replies, follows instructions and keeps the conversation coherent. Despite its compact size, the model is multilingual and handles Russian confidently, which is convenient for international products. It suits a high volume of messages where speed and price matter more than depth of answer.