Z.AI

GLM 5.3

Flagship GLM: very large context and reasoning

Text

Reasoning

Tools

Type: Chat
Context: 1.3M tokens
Russian: medium
Input price: 59,5 ₽ / 1M tokens
Output price: 187 ₽ / 1M tokens
Release date: August 14, 2026

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: "glm-5.3",
  messages: [{ role: "user", content: "Hi!" }],
  stream: true,
})
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

About the model

GLM 5.3 is the flagship model of Z.AI's GLM line, with reasoning and the largest context in the catalog: over 1.3 million tokens. Entire repositories, long correspondence and bulky collections of documents fit into it, with no need to split them into parts. It helps confidently with code, follows instructions and calls tools reliably (function-calling) for agent scenarios. Input is text. It handles Russian at a medium level.