Use Chatbox with DaoXE

Chatbox's Custom Provider takes an API host and a key — which is exactly what DaoXE is. Set it once and Chatbox's model picker can reach GPT, Claude, Gemini, DeepSeek and the rest of your account's catalogue on one balance (cheapest APIs guide).

Why route Chatbox through DaoXE#

• Desktop, local history. Conversations stay on your machine; only inference goes out.
• One key, many vendors. No per-vendor accounts or cards inside the client.
• Group chats & prompts. Chatbox's prompt library and multi-model group chats run across vendors from one endpoint.

Set it up in Chatbox#

1. Open settings. Chatbox → Settings → Model Provider → choose Custom Provider (or add a provider).
2. Set the API host. Enter https://daoxe.com/v1 — end at /v1; Chatbox appends /chat/completions.
3. Paste the key. Your DaoXE key. Leave the model list to auto-fill, or paste exact IDs from GET /v1/models.
4. Test one call. Send a short message; then check the response's model field matches what you asked for.

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."}]
  }'

Frequently asked questions#