Quick Start

Tired of limits? GLM Coding Plan — monthly access to world-class models, compatible with top coding tools like Claude Code and Cline. All from just $10/month. Try it now →

Getting Started

Get API Key

Access Z.AI Open Platform, Register or Login.
Access Billing Page to top up if needed.
Create an API Key in the API Keys management page.
Copy your API Key for use.
Z.AI Open Platform
Access Z.AI Open Platform, Register or Login.
API Keys Management
Create an API Key in the API Keys management page.

Choose Model

The platform offers multiple models, and you can select the appropriate model based on your needs. For detailed model introductions, please refer to the Models & Agents.

GLM-5

Zai’s new-generation flagship foundation model, targeting Agentic Engineering, enables a paradigm shift from code to engineering.

GLM-4.6V

New multimodal model with 128K training context window and SOTA vision understanding

GLM-Image

Supports text-to-image generation, achieving open-source state-of-the-art (SOTA) in complex scenarios

CogVideoX-3

New frame generation capabilities that significantly improve image stability and clarity

Choose the Calling Method

Our platform provides various development approaches; you can select the best fit for your project needs and tech stack.

HTTP API

Standard RESTful API, compatible with all programming languages.

Z.AI Python SDK

Official Python SDK, featuring full type hints and async support.

Z.AI Java SDK

Official Java SDK, designed for high concurrency and availability.

OpenAI Python SDK

OpenAI SDK Compatibility, quickly migrating from OpenAI.

API Reference

Complete API documentation with parameter descriptions.

Make API Call

After preparing your API Key and selecting a model, you can start making API calls. Here are examples using curl, Python SDK, and Java SDK:

Note: When using the GLM Coding Plan, you need to configure the dedicated
Coding endpoint - https://api.z.ai/api/coding/paas/v4
instead of the general endpoint - https://api.z.ai/api/paas/v4
Note: The Coding API endpoint is only for Coding scenarios and is not applicable to general API scenarios. Please use them accordingly.

curl -X POST "https://api.z.ai/api/paas/v4/chat/completions" \
-H "Content-Type: application/json" \
-H "Accept-Language: en-US,en" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
    "model": "glm-5",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful AI assistant."
        },
        {
            "role": "user",
            "content": "Hello, please introduce yourself."
        }
    ]
}'

Install SDK

# Install latest version
pip install zai-sdk

# Or specify version
pip install zai-sdk==0.1.0

Verify Installation

import zai
print(zai.__version__)

Usage Example

from zai import ZaiClient

# Initialize client
client = ZaiClient(api_key="YOUR_API_KEY")

# Create chat completion request
response = client.chat.completions.create(
    model="glm-5",
    messages=[
        {
            "role": "system",
            "content": "You are a helpful AI assistant."
        },
        {
            "role": "user",
            "content": "Hello, please introduce yourself."
        }
    ]
)

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

Install SDKMaven

<dependency>
    <groupId>ai.z.openapi</groupId>
    <artifactId>zai-sdk</artifactId>
    <version>0.3.0</version>
</dependency>

Gradle (Groovy)

implementation 'ai.z.openapi:zai-sdk:0.3.0'

Usage Example

import ai.z.openapi.ZaiClient;
import ai.z.openapi.service.model.*;
import java.util.Arrays;

public class QuickStart {
    public static void main(String[] args) {
        // Initialize client
        ZaiClient client = ZaiClient.builder().ofZAI()
            .apiKey("YOUR_API_KEY")
            .build();

        // Create chat completion request
        ChatCompletionCreateParams request = ChatCompletionCreateParams.builder()
            .model("glm-5")
            .messages(Arrays.asList(
                ChatMessage.builder()
                    .role(ChatMessageRole.USER.value())
                    .content("Hello, who are you?")
                    .build()
            ))
            .stream(false)
            .build();

        // Send request
        ChatCompletionResponse response = client.chat().createChatCompletion(request);

        // Get response
        System.out.println(response.getData().getChoices().get(0).getMessage().getContent());
    }
}

Install SDK

# Install or upgrade to latest version
pip install --upgrade 'openai>=1.0'

Verify Installation

python -c "import openai; print(openai.__version__)"

Usage Example

from openai import OpenAI

client = OpenAI(
    api_key="your-Z.AI-api-key",
    base_url="https://api.z.ai/api/paas/v4/"
)

completion = client.chat.completions.create(
    model="glm-5",
    messages=[
        {"role": "system", "content": "You are a smart and creative novelist"},
        {"role": "user", "content": "Please write a short fairy tale story as a fairy tale master"}
    ]
)

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

Install SDK

# Install or upgrade to latest version
npm install openai

# Or using yarn
yarn add openai

Usage Example

import OpenAI from "openai";

const client = new OpenAI({
    apiKey: "your-Z.AI-api-key",
    baseURL: "https://api.z.ai/api/paas/v4/"
});

async function main() {
    const completion = await client.chat.completions.create({
        model: "glm-5",
        messages: [
            { role: "system", content: "You are a helpful AI assistant." },
            { role: "user", content: "Hello, please introduce yourself." }
        ]
    });

    console.log(completion.choices[0].message.content);
}

main();

Install SDKMaven

<dependency>
    <groupId>com.openai</groupId>
    <artifactId>openai-java</artifactId>
    <version>2.20.1</version>
</dependency>

Gradle (Groovy)

implementation 'com.openai:openai-java:2.20.1'

Usage Example

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

public class QuickStart {
    public static void main(String[] args) {
        // Initialize client
        OpenAIClient client = OpenAIOkHttpClient.builder()
            .apiKey("your-Z.AI-api-key")
            .baseUrl("https://api.z.ai/api/paas/v4/")
            .build();

        // Create chat completion request
        ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
            .addSystemMessage("You are a helpful AI assistant.")
            .addUserMessage("Hello, please introduce yourself.")
            .model("glm-5")
            .build();

        // Send request and get response
        ChatCompletion chatCompletion = client.chat().completions().create(params);
        Object response = chatCompletion.choices().get(0).message().content();

        System.out.println(response);
    }
}

Get More

API Reference

Access API Reference.

Python SDK

Access Python SDK Github

Java SDK

Access Java SDK Github

Get Started

Language Models

Vision Language Models

Image Generation Models

Video Generation Models

Image Generation Models

Audio Models

Capabilities

Tools

Agents

Getting Started

Z.AI Open Platform

API Keys Management

GLM-5

GLM-4.6V

GLM-Image

CogVideoX-3

HTTP API

Z.AI Python SDK

Z.AI Java SDK

OpenAI Python SDK

API Reference

Get More

API Reference

Python SDK

Java SDK

Get Started

Language Models

Vision Language Models

Image Generation Models

Video Generation Models

Image Generation Models

Audio Models

Capabilities

Tools

Agents

​Getting Started

Z.AI Open Platform

API Keys Management

GLM-5

GLM-4.6V

GLM-Image

CogVideoX-3

HTTP API

Z.AI Python SDK

Z.AI Java SDK

OpenAI Python SDK

API Reference

​Get More

API Reference

Python SDK

Java SDK

Getting Started

Get More