GLM-5 API

GLM-5 is Zhipu AI next-generation 745B MoE LLM for high-quality text generation and reasoning, optimized for chat, long-form content, and instruction-following tasks.

Modalities: TextText
In / Out price: $1/$3.2per 1M
Context window: 200K tokens
Released: Feb 12, 2026

GLM-5 overview

GLM-5 by Zhipu AI

Designed to power modern AI products, GLM-5 API delivers strong performance across text generation, structured outputs, code understanding, and complex analytical tasks.

GLM-5 specs

Model ID: zhipu/glm-5
Developer: Zhipu AI
Context window: 200,000 tokens
Max output: 128,000 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What Is GLM-5?

GLM-5 is an advanced LLM developed to support complex reasoning, long-context understanding, and multilingual text generation. It combines deep semantic comprehension with strong instruction following, enabling developers to build reliable AI assistants, automation workflows, coding copilots, and knowledge systems. The model is optimized for both conversational AI and structured outputs, making it suitable for chat interfaces, data extraction pipelines, agentic systems, and enterprise integrations.

Performance and Reliability

GLM-5 is optimized for stable inference and predictable behavior in production environments. It demonstrates strong instruction adherence, reduced hallucination patterns compared to earlier-generation models, and improved contextual retention in extended conversations.

Advanced Reasoning and Structured Output

GLM-5 is built to handle analytical tasks, multi-step reasoning, and structured data generation. It can reliably produce JSON outputs, formatted reports, and schema-aligned responses, making it ideal for backend integrations and automation tools.

Long Context Understanding

GLM-5 supports extended context windows, allowing it to process large documents, maintain conversation continuity, and reason over complex multi-paragraph inputs. This makes it well-suited for research assistants, legal document analysis, and enterprise knowledge management systems.

Code Generation and Technical Tasks

GLM-5 performs effectively in code completion, debugging assistance, and technical documentation generation. It supports modern programming workflows and can be integrated into developer tools, CI/CD pipelines, and AI-powered IDE assistants.

AI-Driven Content Generation

Create high-quality blog posts, technical documentation, marketing copy, and multilingual content with strong consistency and structure.

Use cases

GLM-5 is documented as suited to complex systems engineering and long-horizon agentic tasks. It is also described as strong for real-world coding and end-to-end software development tasks.

The model is documented for building agentic applications that use native tool calling, function execution, and long-horizon task planning. It is also suited to office workflows that require stable completion of complex, multi-step tasks across stages.

GLM-5 is documented for roleplay, with support for maintaining character settings consistently over time. It is also documented for text data extraction from complex documents such as contracts, announcements, and financial reports.

Capabilities

Function calling
Streaming
Structured outputs
Reasoning

GLM-5 benchmarks by Artificial Analysis

See how GLM-5 compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#158 / 21959.8Output tokens / second Latency#113 / 2161.55Seconds to first token Humanity's Last Exam#97 / 45829.3%Score GPQA Diamond#124 / 43982%Score

Speed

Output tokens / second

Benchmark results

Compare 13 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

GLM-5 API pricing

GLM-5 pricing in US dollars
Usage	Price	Unit
Input	$1	1M tokens
Output	$3.2	1M tokens
Cached input	$0.2	1M tokens

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

GLM-5 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	$1	$3.2
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 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": "zhipu/glm-5",
  "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": "zhipu/glm-5",
    "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": "zhipu/glm-5",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

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

All posts

GLM-5 FAQ

What is the context window of GLM-5?

GLM-5 has a 200,000 tokens context window and can return up to 128,000 tokens.

What inputs and outputs does GLM-5 support?

GLM-5 takes text as input and returns text.

What is the model ID for GLM-5?

Use zhipu/glm-5 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was GLM-5 released?

GLM-5 became available on February 12, 2026.

How much does GLM-5 cost?

GLM-5 costs $1 input and $3.2 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does GLM-5 support streaming?

Yes, GLM-5 can stream responses as they are generated.

Who created GLM-5?

GLM-5 was built by Zhipu AI.

How many parameters does GLM-5 have?

GLM-5 is a 745B parameter mixture-of-experts (MoE) model.

Start building with GLM-5

Get API key

GLM-5 API

zhipu/glm-5

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": "zhipu/glm-5",
  "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": "zhipu/glm-5",
    "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": "zhipu/glm-5",
    "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 API

GLM-5 overview

GLM-5 by Zhipu AI

GLM-5 specs

What Is GLM-5?

Performance and Reliability

Advanced Reasoning and Structured Output

Long Context Understanding

Code Generation and Technical Tasks

AI-Driven Content Generation

Use cases

Capabilities

GLM-5 benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

GLM-5 API pricing

GLM-5 vs other models: token prices

How to use the GLM-5 API

Build with your agent

1Get your API key

2Make your first request

Related articles

GLM-5 FAQ

Start building with GLM-5

GLM-5 API

Build with your agent

1Get your API key

2Make your first request

GLM-5 API

GLM-5 overview

GLM-5 by Zhipu AI

GLM-5 specs

What Is GLM-5?

Performance and Reliability

Advanced Reasoning and Structured Output

Long Context Understanding

Code Generation and Technical Tasks

AI-Driven Content Generation

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

GLM-5 API pricing

GLM-5 vs other models: token prices

How to use the GLM-5 API

Build with your agent

1Get your API key

2Make your first request

Models similar to GLM-5

GLM 5.3 FlashX

GLM-5.3-Flash

GLM-5.3

Grok Build 0.1

GPT-6.1 Terra

Claude 4.5 Haiku

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

GLM-5 FAQ

Start building with GLM-5