Llama 4 Maverick

The flagship Llama 4 for text and images

Text

Images

Tools

Type: Chat
Context: 1.0M tokens
Russian: medium
Input price: 16 ₽ / 1M tokens
Output price: 55,68 ₽ / 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-maverick",
  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 Maverick is Meta's flagship model in the Llama 4 lineup and works with text and images. It analyzes pictures, screenshots, diagrams and documents with mixed content, answering questions about the visual context. As an all-purpose chat model it holds coherent conversations, generates and edits text, helps with code and keeps a large context. It is multilingual and handles Russian confidently. It supports tool calling and suits assistants and agents that work with images.

Strengths

Works with text and images
Large context for sizable tasks
Strong all-purpose chat
Works with code and data structures
Tool calling for agents
Multilingual, with Russian support

Where to use it

Assistants that analyze images
Analyzing images, screenshots and diagrams
Processing documents with mixed content
Complex conversations and content generation
Agent scenarios with tool calling
Help with code and data

Other models

Whole catalog

Llama 4 Scout