GLM 5.2
Zhipu
zhipu/glm-5.2
1M-context hybrid reasoning agent model
Context Window
1.0M
1,000,000 tokens
Max Output
16K
16,384 tokens
About this model
GLM-5.2 latest — 1M-context hybrid reasoning agent model on Bailian
This model supports a 1M-token context window with both thinking and non-thinking modes. It is suited for long-context agents, complex tool use, structured output, and coding/reasoning workflows. Bailian documents Function Calling, structured output, and implicit cache support.
Access it through Chuizi.AI with a single ck- API key — no separate Alibaba Cloud Bailian or Zhipu AI account needed.
Highlights
1M context window
Hybrid reasoning modes
Function Calling
Structured output
Implicit cache
Best For
Long-context agentsComplex coding tasksTool orchestrationStructured data generation
2026-06-17
Capabilities
ChatReasoningCodetoolscache
Pricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $1.17 |
| Output / 1M | $4.08 |
| Cache Read | $0.233 |
Final prices shown
Quick Start
main.py
from openai import OpenAI client = OpenAI( base_url="https://api.chuizi.ai/v1", api_key="ck-your-key-here", ) response = client.chat.completions.create( model="zhipu/glm-5.2", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)