> ## Documentation Index
> Fetch the complete documentation index at: https://ngrok.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Tencent TokenHub with the AI Gateway

> Call Tencent TokenHub models through the ngrok AI Gateway with ngrok.ai credits or your own Tencent TokenHub API key.

[Tencent TokenHub](https://www.tencentcloud.com/document/product/1300) 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.

> [!NOTE]
>
> 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

### 1. Create an access key and add credits

Follow the [quickstart](https://ngrok.com/docs/ai-gateway/quickstart.md) to create an access key and purchase [credits](https://ngrok.com/docs/ai-gateway/concepts/credits.md) in [app.ngrok.ai](https://app.ngrok.ai).

### 2. 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](https://www.tencentcloud.com/document/product/1300) account. Then [add a provider key](https://ngrok.com/docs/ai-gateway/guides/attaching-provider-keys.md#add-a-provider-key) and [create an access key configuration](https://ngrok.com/docs/ai-gateway/guides/access-key-configurations.md#create-a-configuration) with a `tokenhub` routing rule that uses it.

### 3. Send requests

Send requests with your access key:

```python theme={"theme":{"light":"css-variables","dark":"css-variables"}}
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](https://ngrok.com/docs/ai-gateway/reference/model-catalog.md#tencent-tokenhub).

## Next steps

* [Provider keys](https://ngrok.com/docs/ai-gateway/guides/attaching-provider-keys.md)
* [Access key configurations](https://ngrok.com/docs/ai-gateway/guides/access-key-configurations.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.