Llama 4 Scout

The light Llama 4: images and long context

Text

Images

Tools

Type: Chat
Context: 1.3M tokens
Russian: medium
Input price: 8 ₽ / 1M tokens
Output price: 24 ₽ / 1M tokens
Release date: April 2025

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: "llama-4-scout",
  messages: [{ role: "user", content: "Hi!" }],
  stream: true,
})
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

About the model

Llama 4 Scout is the lighter model in the Llama 4 lineup, with image support and an especially long context. It answers quickly, costs little and understands pictures, screenshots and documents with visual elements. The large context window suits sizable materials and long conversations. The model is multilingual, handles Russian confidently and follows instructions.

Strengths

Works with text and images
Especially long context
High speed and low cost
Writes in Russian and other languages
Stable on sizable materials

Where to use it

Chats and assistants with images
Processing documents with pictures and diagrams
Working with long materials and correspondence
Quick prototypes and demos
Extracting data from visual documents
Bulk image analysis

Other models

Whole catalog

Llama 4 Maverick