GLM 5.2 API

GLM-5.2 is Zhipu AI flagship MoE LLM with a 1M-token context window, optimized for agentic coding, tool use, reasoning, and long-context tasks.

Modalities: TextText
In / Out price: $1.4/$4.4per 1M
Context window: 1M tokens
Released: Jun 16, 2026

GLM 5.2 overview

GLM 5.2 by Zhipu AI

Handles long documents and multi-step agent workflows, with thinking mode on by default, function calling, and structured output.

GLM 5.2 specs

Model ID: alibaba/glm-5.2
Developer: Zhipu AI
Context window: 1,000,000 tokens
Max output: 131,072 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What Is GLM 5.2 API?

GLM-5.2 is described by Alibaba Cloud as the latest flagship model from Zhipu AI for long-horizon tasks, with support for an ultra-long 1M context window and strong logical reasoning, long-text comprehension, and code generation.

Alibaba Cloud also states that GLM-5.2 is a text-to-text model and that it can be accessed through OpenAI-compatible, DashScope, and Anthropic-compatible interfaces.

Technical Reference

Developer	Zhipu AI
Model ID	alibaba/glm-5.2
Release Date	June 15, 2026
Context Window	1,000,000 tokens (~1M)
Max Output Tokens	131,072 tokens
Modalities	Text → Text
Capabilities	parallel tool calls, reasoning, streaming, structured (JSON schema) output, tool/function calling

What GLM 5.2 Brings to the Table

Long-horizon focus
The model is positioned for long-horizon tasks and is described as suitable for situations that require sustained reasoning over long inputs.

1M context window
Alibaba Cloud documents GLM-5.2 as supporting a 1M context window, and the model overview calls it the latest GLM model with a context length of 1M.

Reasoning and code generation
The model is described as having powerful logical reasoning, long-text comprehension, and code generation capabilities.

Thinking mode
Alibaba Cloud says GLM-5.2 has thinking mode enabled by default, returns `reasoning_content` before the final answer, and supports the `reasoning_effort` parameter.

Where GLM 5.2 Makes the Most Sense

Complex enterprise workflows
Alibaba Cloud describes GLM-5.2 as suitable for intelligent interaction and enterprise applications, which aligns with its long-horizon reasoning and long-text handling focus.

Developer assistance
The model is presented as useful for development assistance, especially for code generation and multi-step reasoning tasks.

Agentic tool use
GLM-5.2 supports Function Calling and, through the Responses API, can use tools such as web search, web extractor, and code interpreter.

Streaming interactions
Alibaba Cloud documents support for streaming and the `tool_stream` parameter, which incrementally returns tool-call arguments during streamed generation when enabled.

Use cases

GLM 5.2 is documented as suited to AI applications and copilots, content creation, workflow automation, and video generation pipelines. It is also described as well-suited for agentic coding, tool use, reasoning, and long-context tasks. Alibaba Cloud’s documentation says it is suitable for intelligent interaction, enterprise applications, and development assistance scenarios. NVIDIA’s catalog describes it as a fit for AI agent systems, chatbots, and applications requiring advanced reasoning and long-context understanding.

Capabilities

Reasoning
Streaming

GLM 5.2 benchmarks by Artificial Analysis

See how GLM 5.2 compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#124 / 21988.2Output tokens / second Latency#123 / 2161.73Seconds to first token Humanity's Last Exam#44 / 45841.1%Score GPQA Diamond#49 / 43989.5%Score

Speed

Output tokens / second

Benchmark results

Compare 11 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

GLM 5.2 API pricing

GLM 5.2 pricing in US dollars
Usage	Price	Unit
Input	$1.4	1M tokens
Output	$4.4	1M tokens
Cached input	$0.28	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

GLM 5.2 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
GLM 5.2	$1.4	$4.4
GLM-5.3-Flash	$0.15	$0.5
GLM 5.3 FlashX	$0.37	$1.25
GLM-5.3	$1.4	$4.4
GLM 5.2 Fast Preview	$3.5	$11

How to use the GLM 5.2 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "alibaba/glm-5.2",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "alibaba/glm-5.2",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "alibaba/glm-5.2",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

GLM 5.2 FAQ

What is the context window of GLM 5.2?

GLM 5.2 has a 1,000,000 tokens context window and can return up to 131,072 tokens.

What inputs and outputs does GLM 5.2 support?

GLM 5.2 takes text as input and returns text.

What is the model ID for GLM 5.2?

Use alibaba/glm-5.2 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was GLM 5.2 released?

GLM 5.2 became available on June 16, 2026.

How much does GLM 5.2 cost?

GLM 5.2 costs $1.4 input and $4.4 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does GLM 5.2 support streaming?

Yes, GLM 5.2 can stream responses as they are generated.

Who created GLM 5.2?

GLM 5.2 was built by Zhipu AI.

Start building with GLM 5.2

Get API key

GLM 5.2 API

alibaba/glm-5.2

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "alibaba/glm-5.2",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "alibaba/glm-5.2",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "alibaba/glm-5.2",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

GLM 5.2 API

GLM 5.2 overview

GLM 5.2 by Zhipu AI

GLM 5.2 specs

What Is GLM 5.2 API?

Technical Reference

What GLM 5.2 Brings to the Table

Where GLM 5.2 Makes the Most Sense

Use cases

Capabilities

GLM 5.2 benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

GLM 5.2 API pricing

GLM 5.2 vs other models: token prices

How to use the GLM 5.2 API

Build with your agent

1Get your API key

2Make your first request

GLM 5.2 FAQ

Start building with GLM 5.2

GLM 5.2 API

Build with your agent

1Get your API key

2Make your first request

GLM 5.2 API

GLM 5.2 overview

GLM 5.2 by Zhipu AI

GLM 5.2 specs

What Is GLM 5.2 API?

Technical Reference

What GLM 5.2 Brings to the Table

Where GLM 5.2 Makes the Most Sense

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

GLM 5.2 API pricing

GLM 5.2 vs other models: token prices

How to use the GLM 5.2 API

Build with your agent

1Get your API key

2Make your first request

Models similar to GLM 5.2

GLM 5.3 FlashX

GLM-5.3-Flash

GLM-5.3

ERNIE 5.0

Qwen3.5 Omni Plus

Mistral Large 4

GLM 5.2 FAQ

Start building with GLM 5.2