Z.ai: GLM 5.2

Name: GLM 5.2 API
Brand: z-ai
Price: 1.4 USD
Availability: InStock

API 使用

使用以下代码示例接入我们的 API：

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

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

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

模型介绍

GLM 5.2 is Z.ai’s latest large-scale reasoning model, designed for long-context understanding, advanced coding, and complex agent workflows. With support for a 1M-token context window and configurable reasoning levels, it can maintain project-scale context across extended interactions, making it well-suited for software engineering, research, automation, and multi-step problem solving.

The model supports both High and XHigh reasoning modes, with XHigh enabling its maximum reasoning capability. GLM 5.2 excels at code generation, tool use, structured outputs, and long-horizon task execution, allowing developers to build sophisticated AI agents and automation systems that operate reliably over large amounts of context.

This model is available through the WaveSpeed AI OpenAI-compatible API and can be integrated into existing applications with minimal changes.

Why Choose GLM 5.2

Massive 1M-token context window for large documents, repositories, and long-running workflows
Strong reasoning performance for coding, planning, and complex multi-step tasks
Optimized for agentic applications with function calling and tool-use support
Structured output generation for JSON-based workflows and schema-constrained responses
Flexible reasoning controls for balancing speed, cost, and reasoning depth
Competitive pricing for large-context production workloads

Key Features

Context Window: 1,048,576 tokens
Max Input: 786,432 tokens
Max Output: 262,144 tokens
Architecture: Text → Text
Function Calling: Supported
Structured Outputs: Supported
Reasoning Controls: Supported
Vision: Not listed
Audio Input: Not listed
Image Generation: Not listed

Specifications

Specification	Value
Provider	chatglm
Model Type	Chat Completions
Architecture	Text → Text
Context Window	1,048,576 tokens
Max Input	786,432 tokens
Max Output	262,144 tokens
Input	Text
Output	Text
Function Calling	Supported
Structured Outputs	Supported

API Integration

Base URL

https://llm.wavespeed.ai/v1

Endpoint

POST /chat/completions

Model ID

z-ai/glm-5.2

Common Use Cases

AI coding assistants
Software engineering agents
Large-scale codebase analysis
Research and document intelligence
Workflow automation
Multi-agent systems
Structured data extraction
Long-context reasoning applications

Notes

Model ID: z-ai/glm-5.2
Provider: chatglm

GLM 5.2 API

z-ai/glm-5.2

GLM 5.2 is Z.ai’s most advanced reasoning model, built for long-context, agentic, and engineering-intensive workloads. With support for a 1M-token context window and configurable High/XHigh reasoning modes, it delivers state-of-the-art performance in coding, tool use, and complex task execution.From requirements gathering and architecture design to implementation, testing, and multi-platform deployment, GLM 5.2 can maintain project-level context and consistently follow engineering best practices throughout the entire software development lifecycle.

关于 GLM 5.2 的常见问题

GLM 5.2 API 多少钱?+

WaveSpeedAI 定价:输入每百万 token $1.40,输出每百万 token $4.40。Prompt 缓存和批处理单独计费,可显著降低长上下文、高重复任务的实际成本。

GLM 5.2 的上下文窗口是多大?+

GLM 5.2 单次请求最多支持 1049K 上下文 token,输出最多 262K token。

GLM 5.2 是否兼容 OpenAI?+

是的。WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容端点提供 GLM 5.2。把官方 OpenAI SDK 的 base URL 指向该地址,使用 WaveSpeedAI 的 API Key 即可,无需任何其他代码改动。

如何开始使用 GLM 5.2?+

登录 WaveSpeedAI,在 Access Keys 中生成 API Key,使用上方显示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 发送请求。新账户可获得免费额度,用于试用 GLM 5.2。

定价

试用模型