Z.ai

Z.ai, formerly Zhipu AI, builds the open-weight GLM family of models for agents, reasoning, and coding. Z.ai supports Chat Completions requests.

Z.ai is a built-in provider you can pay for with credits, so a provider key is optional. Add your own Z.ai key to bill usage to your Z.ai account instead of your ngrok.ai credits.

Setup

Create an access key and add credits

Follow the quickstart to create an access key and purchase credits in app.ngrok.ai.

Store your Z.ai API key (optional)

Skip this step to pay with credits. To bring your own key, create an API key in your Z.ai account. Then add a provider key and create an access key configuration with a z-ai routing rule that uses it.

Send requests

Send requests with your access key:

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.ngrok.ai/v1",
    api_key="ng-xxxxx-g1-xxxxx",
)

response = client.chat.completions.create(
    model="z-ai:glm-5.3",
    messages=[{"role": "user", "content": "Hello!"}]
)

QwenCloud, Tencent TokenHub, and Mistral AI also serve GLM models, so the z-ai: prefix keeps the request on Z.ai.

Available models

See the model catalog.

Concepts

Getting Started With

SDKs

Agents

Guides

Observability

Examples

Reference

API Reference

Setup

Create an access key and add credits

Store your Z.ai API key (optional)

Send requests

Available models

Next steps

​Setup

Create an access key and add credits

Store your Z.ai API key (optional)

Send requests

​Available models

​Next steps

Setup

Available models

Next steps