DaoXEMsty runs local models through its bundled service and remote providers through one settings screen. The provider type to pick is Open AI Compatible — name, API endpoint, key — and DaoXE fits that shape exactly (cheapest APIs guide).
Why route Msty through DaoXE#
- Local and remote in one picker. DaoXE's catalogue sits next to your offline models in the same model selector.
- Workspaces isolate keys. Each Msty workspace carries its own API keys, so a shared machine can keep one DaoXE key per team.
- Model-level extras. Per-model categories (Text / Embedding / Vision / Coding) and extra JSON parameters ride along with a custom provider.
Set it up in Msty#
- Open Settings → Remote Model Providers. Open settings from the sidebar and click Remote Model Providers.
- Add a provider. Click Add New Provider (top right). From the Models Provider dropdown select Open AI Compatible — the same flow Msty's own docs use for SambaNova.
- Fill name, endpoint, key. Name
DaoXE; API endpointhttps://daoxe.com/v1(Msty's documented examples all end in/v1, e.g.https://api.sambanova.ai/v1); paste your DaoXE key. - Add the models. Use the Fetch Models button first — when it works, the model names populate automatically. Otherwise add each model manually with the exact ID from
GET /v1/models, then click Add.
Caveats worth knowing
Fetch Models is the gate: Msty's own docs note it "cannot fetch them automatically" when a provider exposes no usable /v1/models — if the picker stays empty, add each model by exact ID, manually. The endpoint keeps /v1: every documented Open AI Compatible example ends with the version path; a bare host will 404. Keys live in the keychain: Msty saves keys per workspace in the device keychain — an imported workspace on another machine throws "Error while decrypting the ciphertext" until keys are re-entered (or saved unencrypted deliberately). Registry ≠ your account: Msty's model registry is separate from provider entries; a registry update will not add your DaoXE models. More clients: client setup notes.
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 outside the app, then diff a hard 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."}]
}'Verify us — don't trust us
Point the open benchmark at DaoXE and at the official API and compare at temperature 0. Then learn to detect model swapping so a cheaper endpoint can't quietly swap you to a smaller model.
Frequently asked questions#
Can Msty use DaoXE?
Yes — Settings → Remote Model Providers → Add New Provider → Open AI Compatible, with https://daoxe.com/v1 and your DaoXE key.
Why is the model list empty?
Msty fetches models from the provider's /v1/models; if that request fails or returns nothing, the picker stays empty. Add the model manually with the exact ID — that's the documented fallback.
Does the API endpoint include /v1?
Yes — Msty's documented Open AI Compatible examples all end in /v1 (e.g. https://api.sambanova.ai/v1). Keep the version path.
What does it cost?
Per-model, account-scoped — live pricing; top-up is a flat 1 RMB = $1 of credit on every payment method.
Try DaoXE — and benchmark it yourself
One key for GPT, Claude, Gemini, DeepSeek and more. Point the open benchmark at us and compare — don't take our word for it.