DaoXELobeChat's provider settings speak OpenAI-compatible HTTP, so DaoXE slots in as a custom endpoint: paste the key, point the URL, and its model-fetching reads GET /v1/models straight from your account. It's the fastest way to give a non-technical audience one clean door to many models — the pricing side of that door is cheapest APIs guide.
Why route LobeChat through DaoXE#
- The picker becomes your catalogue. Whatever your key can call shows up — nothing that it can't.
- Self-host or use theirs. Both LobeChat's hosted app and your own Docker instance take the same endpoint.
- Vision and tools where supported. Multimodal and function-calling models from the catalogue behave as themselves.
Set it up in LobeChat#
- Open provider settings. LobeChat Settings → Language Models → OpenAI (or add a custom-compatible provider).
- Key + endpoint. Paste your DaoXE key and set the endpoint to
https://daoxe.com/v1. - Fetch the models. Use LobeChat's model-list fetch — it reads
GET /v1/modelsfor your key. Tick the IDs you want in the picker. - Run a vision and a tool test. Send an image to a vision-capable ID and a tool task to check behaviour before pointing teammates at it.
Caveats worth knowing
The endpoint ends at /v1. Only tick model IDs you actually have — LobeChat shows checked models to everyone using the instance, and a missing ID fails mid-conversation. Embedding-dependent features (knowledge base) need an embedding-capable ID. Model list is account-scoped: GET /v1/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 from outside the UI, then compare a hard prompt at temperature 0 against the official API:
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 LobeChat use DaoXE?
Yes — it's a custom OpenAI-compatible endpoint: key plus https://daoxe.com/v1, then fetch the model list.
Does the model list fill automatically?
It fetches GET /v1/models with your key. Enable the IDs you want; the fetch only shows what your account can actually call.
Image input works?
With a vision-capable model ID from the catalogue — and only on conversations using that model.
What does it cost?
Per-model and 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.