DaoXEClaude runs through DaoXE either with the OpenAI SDK (just change the base URL) or via native /v1/messages. Use Messages for Claude Code and Anthropic SDKs; use chat for OpenAI-shaped clients. Prices live on the pricing page — current advantage typically ~30–80% below list via low-price groups. Where savings really come from: the cheapest APIs guide.
Call Claude through DaoXE#
The OpenAI-compatible path is /v1/chat/completions with a Bearer key. The native path is /v1/messages with x-api-key and anthropic-version headers. For Claude Code, point ANTHROPIC_BASE_URL at the host root — it appends the path itself.
curl --fail-with-body --show-error --silent \
https://daoxe.com/v1/messages \
-H "x-api-key: ${DAOXE_API_KEY}" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "YOUR_EXACT_MODEL_ID",
"max_tokens": 64,
"messages": [{"role": "user", "content": "Reply with OK."}]
}'# Claude Code reads the host ROOT; it appends /v1/messages itself
export ANTHROPIC_BASE_URL="https://daoxe.com"
export ANTHROPIC_AUTH_TOKEN="your_api_key" # some builds read ANTHROPIC_API_KEY
# optional: pin exact catalog IDs from GET /v1/models
export ANTHROPIC_MODEL="paste_exact_model_id_here"
export ANTHROPIC_SMALL_FAST_MODEL="paste_small_model_id_here"
claudeClaude-specific notes#
- Claude Code uses the host ROOT (
https://daoxe.com), not.../v1— it appends/v1/messagesitself. See the Cursor & Claude Code guide. - Native Messages headers differ:
x-api-key+anthropic-version, not aBearertoken (that's the chat path). - Extended thinking is opt-in. Enable it per request when you need visible reasoning; otherwise you get a normal answer.
- Use exact IDs from
GET /v1/models— don't hardcode a version string copied from a blog post.
Payment & real cost#
Alipay / WeChat Pay / USDT — a flat 1 RMB = $1
Every method tops up at a flat 1 RMB = $1 of credit, while models bill at their official USD price. At a real ~7 RMB/USD rate, Western flagships (GPT / Claude / Gemini / Grok) come out around 1/7 of official cost (≈85% off) — and because USDT tops up the same way, USD holders abroad get the same deal. Honest caveat: cheaper domestic models (DeepSeek / Qwen / GLM) still beat going direct, just by less — it is not “everything is 1/7”. Rates move; daoxe.com/pricing is authoritative, and a small top-up verifies it.
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}"Run the same hard-reasoning prompt through DaoXE and the official Anthropic API at temperature 0 and diff the outputs — that's how you prove it's really Claude:
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 I use Claude with the OpenAI SDK?
Yes — set the base URL to https://daoxe.com/v1 and call /v1/chat/completions with a Claude model ID.
Does Claude Code work through DaoXE?
Yes, natively via /v1/messages. Set ANTHROPIC_BASE_URL=https://daoxe.com (host root). Full steps in the Cursor & Claude Code guide.
x-api-key or Bearer?
Native Messages uses x-api-key + anthropic-version; the OpenAI-compatible chat path uses a Bearer token.
How much does Claude cost here?
Per-model, account-scoped — see live pricing. Current advantage vs official: typically ~30–80% below list via low-price groups.
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.