DaoXEBecause DaoXE mirrors the OpenAI API, GPT is a one-line change: point the base URL at https://daoxe.com/v1, keep your code. The same key also reaches Claude, Gemini, DeepSeek and more — see the cheapest APIs guide for cost routing.
Call GPT through DaoXE#
Use /v1/chat/completions for the classic Chat API, or /v1/responses for projects on the Responses API. Reasoning behavior (o-series / gpt-5) is selected by the model ID, not a separate endpoint.
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."}]
}'curl --fail-with-body --show-error --silent \
https://daoxe.com/v1/responses \
-H "Authorization: Bearer ${DAOXE_API_KEY}" \
-H "Content-Type: application/json" \
-d '{
"model": "YOUR_EXACT_MODEL_ID",
"input": "Say hello in one sentence."
}'from openai import OpenAI
client = OpenAI(
base_url="https://daoxe.com/v1", # one base URL for every model
api_key="YOUR_DAOXE_KEY",
)
resp = client.chat.completions.create(
model="YOUR_EXACT_MODEL_ID", # from GET /v1/models
messages=[{"role": "user", "content": "Hello"}],
max_tokens=64,
)
print(resp.choices[0].message.content)GPT-specific notes#
- Two protocols. Chat Completions and Responses are both exposed — pick whichever your client speaks.
- Reasoning is per model ID. Pick the reasoning variant by its ID; there's no magic switch.
- Some clients default to /responses. If a client errors on Responses, force
/chat/completionsin its settings. - Exact IDs only. Read them from
GET /v1/modelsfor your account.
What it costs#
One balance, one top-up rate
Top-up runs at a flat 1 RMB = $1 of credit on every payment method, and each model then bills at its own USD rate — live per-model rates are on the live pricing page. That rate is the same on Alipay, WeChat Pay, USDT, bank card (Visa · Mastercard), Apple Pay and Google Pay — one balance, shared by every model in the catalog, with no plan to choose and no monthly minimum. Rates are account-scoped and do change, so confirm with one small top-up rather than trusting a number in a guide.
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, then diff a fixed prompt against the official OpenAI API at temperature 0 to confirm you get the same model class:
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#
Will my OpenAI code work unchanged?
Yes — change the base URL to https://daoxe.com/v1 and keep the SDK calls; use exact model IDs.
Chat Completions or Responses?
Both are available. Use whichever your client expects; force chat if a client mishandles Responses.
How do reasoning models work?
Select the reasoning variant by its model ID from GET /v1/models; there's no separate flag.
How much does GPT cost here?
Per model, account-scoped — see 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.