Tencent TokenHub

Tencent TokenHub serves models from several labs under one API key, including Tencent Hunyuan, Z.ai GLM, Moonshot AI Kimi, DeepSeek, MiniMax, Xiaomi MiMo, and StepFun. Tencent TokenHub supports Chat Completions, Responses, and Anthropic Messages requests.

Tencent TokenHub is a built-in provider you can pay for with credits, so a provider key is optional. Add your own TokenHub key to bill usage to your Tencent Cloud 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 TokenHub API key (optional)

Skip this step to pay with credits. To bring your own key, create a TokenHub API key in your Tencent Cloud account. Then add a provider key and create an access key configuration with a tokenhub 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="tokenhub:tencent/hy3",
    messages=[{"role": "user", "content": "Hello!"}]
)

Many TokenHub models are also served by their own labs. Add the tokenhub: prefix, as in tokenhub:moonshotai/kimi-k3, to keep the request on TokenHub.

Available models

See the model catalog.

Concepts

Getting Started With

SDKs

Agents

Guides

Observability

Examples

Reference

API Reference

Setup

Available models

Next steps

​Setup

​Available models

​Next steps

Setup

Available models

Next steps