Cherry Studio

Open-source desktop client (Win / macOS / Linux). Add an OpenAI-type provider to connect.

Prerequisites

Signed in with balance · key created in the right group (create a key) · model IDs from the models table or /v1/models

Download & install

Download from cherry-ai.com or GitHub Releases (CherryHQ/cherry-studio). All three desktop platforms are supported.

Setup steps

1
Open Settings → Model Services, click Add at the bottom and pick provider type OpenAI.
2
Set API address to https://api.daoxe.com. Cherry Studio appends /v1 automatically; a trailing / disables the append, a trailing # forces the URL as-is.
3
Paste your sk-xxxx key into the API key field.
4
In the provider's Models section click Add and type the model ID manually (the dropdown won't list it automatically).
5
Hit Check to run a connectivity test, then pick the model in a chat.

Choosing models

Model IDs must match the site exactly (case-sensitive). Copy them from the recommended models table or GET /v1/models. If the key's group doesn't include the model you'll get 403 / model not available — see Models & groups.

Common pitfalls

The trailing-slash rule is the top gotcha: entering https://api.daoxe.com/v1 and letting the app append again yields /v1/v1 → 404. Just use https://api.daoxe.com.
For translation / quick actions, switch to a cheap fast model to avoid burning quota or hitting 429 rate limits.

UI reference

Cherry Studio provider settings — Cherry Studio · provider settings · Click image to enlarge