Google

Gemma 4 26B

Open Gemma 4: reasoning, text and images

Text

Images

Video

Reasoning

Tools

Type: Chat
Context: 262K tokens
Russian: high
Input price: 5,6 ₽ / 1M tokens
Output price: 27,2 ₽ / 1M tokens
Release date: April 2026

Start for free Try in the Playground

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: "gemma-4-26b",
  messages: [{ role: "user", content: "Hi!" }],
  stream: true,
})
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

About the model

Gemma 4 26B is Google's new-generation open model from the Gemma family, which is built on the technology of the Gemini lineup. It works with text and images: it analyzes pictures, screenshots and documents with visual elements. Unlike earlier Gemma models, the fourth generation supports reasoning and switches on step-by-step analysis for complex multi-step tasks. The model supports many languages, works confidently with Russian and reliably calls tools (function-calling), so it suits agents and integrations. Its weights are open: you can run the model yourself.