DaoXECopilot's Settings → Copilot → BYOK → Add a provider → Add a custom provider takes a base URL, a key, and model IDs — which is exactly what DaoXE is. Configure it once and Quick Chat and agent features reach GPT, Claude, Gemini, DeepSeek and the rest of your account's catalogue on one balance (cheapest APIs guide).
Why route Obsidian Copilot through DaoXE#
- AI where your notes live. Chat, edit and summarise against your vault without copying text to another app.
- One key, many vendors. No per-vendor accounts inside the plugin.
- Keys stay in the Keychain. Copilot stores BYOK keys in the device's Obsidian Keychain, not in the vault's
data.json— vault sync doesn't carry your credentials.
Set it up in Obsidian Copilot#
- Open the BYOK settings. Obsidian → Settings → Copilot → BYOK → Add a provider → Add a custom provider.
- Set the base URL and key. Enter
https://daoxe.com/v1and your DaoXE key. Base URLs end at/v1— the plugin appends the paths itself. - Add exact model IDs. Model discovery reads the endpoint's
/v1/modelsresponse; if listing fails, paste an exact ID fromGET /v1/modelsmanually — guessed names fail. - Test, then curate. Click Test and Save. New models are enabled for Quick Chat and agent features by default; curate the lists under Basic → Agents.
Caveats worth knowing
CORS toggle: if Test succeeds but chat cannot send, edit the provider and enable Enable CORS — responses then arrive after completion instead of streaming token by token. Agent routing: Copilot passes saved keys to its agent backend at startup; a model the backend cannot route stays out of the agent list but may still work in Quick Chat. Key storage: keys live in this device's Keychain, not the vault — removing them is Advanced → API Key Storage. Model IDs are account-scoped. 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 client, 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 Obsidian Copilot use DaoXE?
Yes — BYOK → Add a custom provider with base URL https://daoxe.com/v1, your key, and exact model IDs.
Why does Test pass but chat fail?
That's the CORS case: enable Enable CORS on the provider. Responses arrive non-streamed after that.
Where is my key stored?
In this device's Obsidian Keychain — not in data.json, so syncing the vault doesn't copy the key.
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.