Set up WorkBuddy (Tencent)
Tencent's AI office agent. Add one custom model to run it on CherryChat
- API format: OpenAI Chat Completions
- Base URL format: Full path to /v1/chat/completions (https://gpt.cherrychat.org/v1/chat/completions)
- Recommended model: claude-sonnet-5-5, gpt-6.1-sol
- Platforms: macOS, Windows
Steps
Open the model settings
Open WorkBuddy and go to Settings → Model (usually via the account menu at the top right), then find the custom models section.
Add a model and choose Custom
Click Add Model and pick Custom in the provider list (not one of the listed providers).
Fill in the URL, API key and model
Enter the full URL ending in /v1/chat/completions. WorkBuddy only speaks this OpenAI-compatible format; use the same URL for Claude models too.
- URL: https://gpt.cherrychat.org/v1/chat/completions (Full path, not just the domain or /v1)
- API key: sk-your-key
- Model name (model ID): claude-sonnet-5-5
Advanced settings
Keep the Custom Protocol switch off. A 128K context is fine. Capability flags are not detected automatically: Claude and GPT models support tool calling, so tick it for them; when unsure, tick less.
Save and test
Save, return to the chat, pick the model from the custom group in the model selector and send "hello"; a reply means it works.
Common pitfalls
- Use the full URL https://gpt.cherrychat.org/v1/chat/completions. With Custom Protocol off, WorkBuddy validates and completes the standard /chat/completions path, so the full URL is safest.
- Only the OpenAI-compatible Chat format works, not the native Claude API; CherryChat Claude models also accept Chat, so keep https://gpt.cherrychat.org/v1/chat/completions.
- Capability flags are manual: without tool calling the agent is limited, and ticking it for a model that lacks it causes errors.
- The config, key included, stays on your computer. Usage is paid from CherryChat credits, not WorkBuddy credits.
- Menu locations may change between WorkBuddy versions; follow what the app shows.
Error → cause → fix
| What you see | Why | What to do |
|---|---|---|
| 401 when saving or chatting | The key is wrong, has spaces, or was disabled | Copy the key again from My Keys and paste it |
| 404 or "request failed" | The URL is only the domain or /v1, or Custom Protocol is on without the full path | Set the URL to https://gpt.cherrychat.org/v1/chat/completions and keep Custom Protocol off |
| Model not found | The model name is misspelled (case or spaces) | Copy it from the Models page, e.g. claude-sonnet-5-5 |
| HTTP 402 or "insufficient balance" (billing_error in Claude format) | Your credits cannot cover this call. API calls are paid from credits only; memberships and unlimited plans do not apply | Top up any amount in the CherryChat Store, then retry after a few seconds |
| HTTP 429 Too Many Requests | Too many requests: by default 120 per minute per key and 8 at a time per account | Lower the concurrency or requests per second in the tool and wait for the Retry-After seconds; most tools retry on their own |
Guide checked 2026-11-02. The tool's screens may change; the official docs win if they differ.
Operated by UK Company CHERRYCHAT LTD · Company Number 16096119 · Support WeChat: JsnonoChat · Content is AI-generated — please verify before relying on it
