GLM-5.2

Zhipu AI's latest flagship model designed for long-horizon tasks, capable of autonomous work for up to 8 hours in a single session.

Overview

GLM-5.2 is Zhipu AI's latest flagship model, designed specifically for Long Horizon Tasks. It can independently and continuously work for up to 8 hours in a single task, autonomously planning, executing, and self-evolving to deliver complete engineering-grade results.

Key Specifications

Parameter	Value
Context Window	200K tokens
Max Output	131K tokens
Input Modalities	Text
Output Modalities	Text

Capabilities

Text Generation — State-of-the-art reasoning and generation
Code Generation — Strong multi-language programming capabilities
Function Calling — Structured tool use for API integrations
JSON Mode — Guaranteed valid JSON output
Thinking Mode — Deep reasoning for complex problem-solving
Streaming — Server-sent events for real-time delivery
Web Search — Integrated search for up-to-date information
Agent — Autonomous task planning and execution

Pricing

Type	Price
Input	$1.12 / 1M tokens
Output	$3.52 / 1M tokens
Cache Read	$0.208 / 1M tokens

Usage Example

from openai import OpenAI

client = OpenAI(
    api_key="sk-...",
    base_url="https://api.yolorouter.com/v1",
)

response = client.chat.completions.create(
    model="glm-5.2",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Best Practices

Ideal for complex multi-step agent tasks, autonomous coding, and long-running engineering projects
Enable thinking mode for complex reasoning tasks
Use context caching for repeated prompts to reduce cost