Use DaoXE in Cherry Studio

Cherry Studio treats DaoXE as an OpenAI-type provider: paste a key, set the API host, and add model IDs. The one thing that trips people up is how Cherry completes the endpoint path — get that right and everything works. See the cheapest APIs guide for splitting cheap and frontier models.

Why route Cherry Studio through DaoXE#

• Local desktop, many providers. Keep your chats local while DaoXE supplies the models.
• One key, many models. Add GPT, Claude, Gemini and DeepSeek IDs under a single DaoXE provider.
• Per-assistant models. Assign different DaoXE models to different assistants to balance cost and quality.

Set it up in Cherry Studio#

1. Add a provider. Settings → Model Providers → Add, choose type OpenAI, and name it DaoXE.
2. Set key & API host. Paste your DaoXE key. For the host, enter https://daoxe.com and let Cherry append the path (see caveat for the exact rule).
3. Add models. Fetch or add exact model IDs from GET /v1/models (e.g. a GPT, a Claude, a DeepSeek ID).
4. Pick a model & test. Select a DaoXE model in a chat and send a message to confirm it responds.

Verify you actually get the model#

Prove the endpoint works before blaming the client — if this fails, no setting will fix it:

export DAOXE_API_KEY="your_api_key"

# List the exact model IDs your account can call
curl --fail-with-body --show-error --silent \
  https://daoxe.com/v1/models \
  -H "Authorization: Bearer ${DAOXE_API_KEY}"

Prove the endpoint independently of Cherry first, then diff a fixed prompt against the official API at temperature 0:

curl --fail-with-body --show-error --silent \
  https://daoxe.com/v1/chat/completions \
  -H "Authorization: Bearer ${DAOXE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_EXACT_MODEL_ID",
    "max_tokens": 64,
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

Frequently asked questions#