Using 知数云 in ChatBox

ChatBox is an open-source AI client that supports Windows, macOS, Linux, iOS, Android, and Web. It supports custom providers of the "OpenAI API" type, so it can directly integrate with 知数云. This article introduces the configuration process.

Application Process

To integrate 知数云 into ChatBox, first go to the 知数云 Console, obtain your API Token, and keep it for later use.

Get 知数云 API Key

If you have not logged in or registered yet, you will be automatically redirected to the login page and invited to register and log in. After logging in or registering, you will automatically return to the current page.

A free quota is provided with the first application, allowing you to experience 知数云's model services for free.

Download ChatBox

Go to the ChatBox official website to download it by platform, or directly use the installation-free Web version:

  • Desktop: Windows .exe, macOS .dmg (Intel / Apple Silicon versions), Linux AppImage
  • Mobile: App Store, Google Play, official website Android direct link

Configure 知数云

Launch ChatBox, go to Settings → Models → Add Custom Provider, set API Mode to OpenAI API Compatible, then fill in:

Field Value Description
API Key Your 知数云 Token The Token copied from the console
API Host https://xapi.zhishuyun.com Enter only the root domain, do not include /openai or /v1
API Path /v1/chat/completions ChatBox defaults to /chat/completions, so you need to manually change it to this

ChatBox 知数云 Provider Configuration Interface

ChatBox's request path is {API Host} + {API Path}, so only enter the root domain in Host:

API Host Final Request Result
https://xapi.zhishuyun.com https://xapi.zhishuyun.com/v1/chat/completions Correct
https://xapi.zhishuyun.com/openai https://xapi.zhishuyun.com/openai/v1/chat/completions 404 (there is no /v1 under /openai)
https://xapi.zhishuyun.com/openai/v1 https://xapi.zhishuyun.com/openai/v1/v1/chat/completions 404

ChatBox does not automatically call /v1/models. You need to manually enter model IDs in the "Custom Models" input box at the bottom of the model settings page (one per line). After saving, you can select them from the model dropdown in the chat interface. Capability toggles, context window, and output limit must be filled in according to the current contract of the selected model; do not copy values from other models.

Select a Model

The model catalog will continue to be updated. Prioritize using the model list automatically loaded by the client; when manual entry is required, first request GET https://xapi.zhishuyun.com/v1/models to obtain the current model IDs, then select according to the context, image, and tool-calling capabilities supported by the client.

Verify the Integration

If you are unsure whether the issue is with ChatBox or the network, you can first use curl to directly verify the endpoint (replace {token} with your Token):

curl -X POST 'https://xapi.zhishuyun.com/v1/chat/completions' \
  -H 'Authorization: Bearer {token}' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "MODEL_ID",
    "messages": [{"role": "user", "content": "ping"}]
  }'

Receiving an OpenAI-compatible chat.completion object indicates that both the Token and endpoint are ready; if HTTP 403 used_up is returned, it means the Token is valid but the balance is insufficient. You can top up in the console.

Frequently Asked Questions

404 Not Found Is Displayed

Usually, /openai or /v1 was unnecessarily added to API Host. Enter only https://xapi.zhishuyun.com for Host, and leave the path as the default /v1/chat/completions.

401 / token_mismatched Is Displayed

Please confirm that the "API Key" contains the 知数云 Token (without the Bearer prefix and without extra spaces), and that the corresponding application's balance is sufficient.

ChatBox does not automatically fetch the model list. You must manually enter the model IDs in the "Custom Models" box and save them.

Want to Generate Images in ChatBox

知数云's image generation is a separate Images API (/openai/images/generations), using a different path from the chat API, and ChatBox's image entry cannot directly integrate with it. If you need to generate images, please refer to the Image Generation API Documentation and call it using curl / SDK.

Learn More