Cherry Studio setup
Cherry Studio is a free chat app for macOS, Windows and Linux. You can talk to any Claudexia model and switch models in one window. No terminal needed.
What you need
- Cherry Studio. Download the installer for your system from cherryai.com/download. This guide is written for version 2.1.
- A Claudexia key. Create one in the dashboard under API keys. Keys start with
sk_cdx_. No account yet? Sign up. - Money on your balance. Top up by card or with crypto, from $1. This helps when payments to the original provider do not go through in your country. Payment options are listed on Pricing.
Steps
- Open settings (the gear icon) → Model Services → Add Provider at the bottom of the list → Add Custom Provider.
- Fill in the fields:
| Field | Value |
|---|---|
| Provider Name | Claudexia |
| API Key | sk_cdx_YOUR_KEY |
| OpenAI (Chat Completions) | https://api.claudexia.tech |
- A Request path line appears under the address field. It should show
https://api.claudexia.tech/v1/chat/completions. Save the provider. - Open Model management and click Sync models to load every Claudexia model. You can also add a single model with Add Model, for example
claude-sonnet-5. - Turn on the provider switch in the top right corner. Without it the provider stays disabled.
Enter the address without /v1 and without a trailing slash: Cherry Studio adds /v1/chat/completions itself. An address with /v1 also works, but a trailing / or # changes how the app builds the URL, so leave them out.
Versions 1.x had a Provider Type dropdown instead of the Endpoint fields: choose OpenAI there and enter the same address https://api.claudexia.tech in API Host.
Check that it works
Start a new chat, choose a Claudexia model at the top and send "Hello". If a reply comes back, it works. The Model Check button next to the key also tests the connection, but it sends real requests, and they cost money.
Which model to pick
- For everyday work:
claude-sonnet-5in the Premium channel. On Cheap useclaude-opus-5-5. - For hard tasks:
claude-opus-5-5orgpt-6-astra. - To spend less:
deepseek-v4.1-flashorgpt-6-luna. Both cost several times less than Sonnet 5.
Prices and the full list are in the model catalog. GPT, DeepSeek, Gemini and other non-Claude models work only with Premium channel keys: see Channels.
Common errors
Click an error to see what to do.
The model list is empty
Check the Request path line under the address and the key. If Sync models does not help, add a model by hand with Add Model, taking the ID from the catalog.
401: Invalid or missing API key
The tool sent a wrong key or no key at all. Copy the whole key from API keys: it starts with sk_cdx_ and has no spaces or line breaks. If the key was deleted or revoked, create a new one. Restart the tool after you change the key.
402: balance is empty
Your balance ran out. In the OpenAI format the error has the code insufficient_quota; in the Anthropic format it is HTTP status 402. Top up under Billing by card or with crypto, from $1. No settings need to change, just send the request again. When the balance is almost empty, requests run one at a time and you may get a 429 with the code low_balance. The code account_frozen means the account is suspended: contact support.
404: Not found or wrong address
The tool calls the wrong address. For this tool the address is https://api.claudexia.tech/v1, ending in /v1 with no slash after it. If the tool adds /v1 on its own, you end up with /v1/v1 and a 404: remove /v1 from the field. The address table for other tools is on Addresses and formats.
The tool does not see the key
Tools read their settings at startup. Quit the tool completely and open it again, and open a new terminal window. An environment variable set in one terminal window is not visible in another. Apps started from the Dock, the Start menu or a shortcut do not read ~/.zshrc or ~/.bashrc: for them, put the key in the tool settings.
Model not found
The model name must match the ID in the catalog exactly: claude-sonnet-5, not "Claude Sonnet 5". Only Claude Code understands the [1m] suffix; leave it out everywhere else.
403: model_not_in_channel
The model is not in your key channel. The Cheap channel serves Claude models only; Premium serves the whole catalog. Switch the model or the key channel: see Premium and Cheap channels.
Check the key without the tool
The command below sends one short request straight to Claudexia, without the tool. It tells you whether the problem is your key and balance or the tool settings. Replace sk_cdx_YOUR_KEY with your key. The request costs a fraction of a cent.
curl https://api.claudexia.tech/v1/chat/completions \
-H "Authorization: Bearer sk_cdx_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-sonnet-5", "max_tokens": 16, "messages": [{"role": "user", "content": "Reply with OK"}]}'Invoke-RestMethod https://api.claudexia.tech/v1/chat/completions -Method Post `
-Headers @{ Authorization = 'Bearer sk_cdx_YOUR_KEY' } -ContentType 'application/json' `
-Body '{"model": "claude-sonnet-5", "max_tokens": 16, "messages": [{"role": "user", "content": "Reply with OK"}]}'You get a reply with a choices field: the key and balance are fine, so look at the tool settings. You get an error: the code and message point to the cause. They are covered above and in the error reference.