Quickstart

Get started with GLM 5.

GLM 5 exposes OpenAI-compatible Chat Completions and Responses APIs through one base URL. Choose the integration style that fits your application:

Using the GLM 5 API

Send standard HTTP requests to https://glm5.app/api/v1/chat/completions. Authenticate with a bearer API key and use a model ID returned by GET /models.

import os
import requests

response = requests.post(
    "https://glm5.app/api/v1/chat/completions",
    headers={
        "Authorization": f"Bearer {os.environ['GLM5_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "model": "glm-5.3-flash",
        "messages": [
            {"role": "user", "content": "Explain why the sky is blue in one paragraph."}
        ],
    },
)

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

The APIs support streaming and function calling on supported models. See Chat Completions and Client Integrations for request schemas and setup details.

Using the OpenAI SDK

Point the standard OpenAI client at the GLM 5 base URL. Your application can keep the familiar chat.completions.create interface.

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.GLM5_API_KEY,
  baseURL: 'https://glm5.app/api/v1',
});

const completion = await client.chat.completions.create({
  model: 'glm-5.3-flash',
  messages: [
    { role: 'user', content: 'Write a hello-world function in TypeScript.' },
  ],
});

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

Using coding clients

Developer tools differ in how they accept custom model providers. Use the dedicated integration guide instead of guessing provider fields.

Building with an AI assistant

If you want an AI coding assistant to configure your local tool, give it the connection values below and ask it to inspect the exact version installed on your machine before changing configuration.

Help me configure GLM5 in my coding tool.

Connection values:
- Base URL: https://glm5.app/api/v1
- Model: glm-5.3-flash
- API key: keep it local in GLM5_API_KEY or the tool's secure credential store

Requirements:
1. Inspect my installed client/version before changing anything.
2. Use its supported custom-provider configuration.
3. Never ask me to paste the API key into chat or commit it to source control.
4. Preserve my existing configuration.
5. If the client cannot use a custom OpenAI-compatible endpoint, explain the limitation and recommend a compatible path.

Next steps