Tokenchuhai
● Tokyo edge · OpenAI-compatible

China's frontier LLMs.
One endpoint. Billed in USD.

DeepSeek-V3, DeepSeek-R1, Doubao, Qwen, GLM-4 — accessible from any OpenAI SDK by changing two lines. No Chinese mobile number, no CNY card, no VPN. Pay-as-you-go from $5.

Free $0.20 credit on signup · No credit card required to start

drop-in.py
from openai import OpenAI

client = OpenAI(
  base_url="https://wutonglu.com/v1",
  api_key="sk-tch-...",
)

resp = client.chat.completions.create(
  model="deepseek-chat",
  messages=[{"role": "user", "content": "Hi"}],
)
print(resp.choices[0].message.content)

Why a gateway?

No Chinese onboarding

Skip the +86 SIM, real-name KYC and CNY-only payment rails. Email signup, USD top-up.

One SDK, four providers

Switch between DeepSeek, Doubao, Qwen and GLM by changing the model string. SSE streaming works out of the box.

Tokyo edge

Closer to Asia/Pacific traffic than US-east relays. ~30–80 ms upstream RTT into mainland clusters.

Available models

Live pricing and full list is at /v1/models.

Model id Provider Context Input / 1M Output / 1M
Loading…

Quickstart

Python · openai
from openai import OpenAI

client = OpenAI(
  base_url="https://wutonglu.com/v1",
  api_key="sk-tch-..."
)

stream = client.chat.completions.create(
  model="deepseek-reasoner",
  messages=[{"role":"user","content":"Explain Bell's theorem in 2 lines."}],
  stream=True,
)
for chunk in stream:
  print(chunk.choices[0].delta.content or "", end="")
Node · openai
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://wutonglu.com/v1",
  apiKey:  "sk-tch-...",
});

const res = await client.chat.completions.create({
  model: "doubao-pro-32k",
  messages: [{ role: "user", content: "Hello in Japanese" }],
});
console.log(res.choices[0].message.content);
curl
curl https://wutonglu.com/v1/chat/completions \
  -H "Authorization: Bearer sk-tch-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-plus",
    "messages": [{"role":"user","content":"Hi"}]
  }'
Compatibility

chat/completions (stream + non-stream)

✓ Tool / function calling (where the upstream supports it)

response_format=json_object

✓ Drop-in SDKs: openai-python, openai-node, LangChain, LiteLLM, Vercel AI SDK

Embeddings and image endpoints land soon — open an issue if you need them.

Pricing

Pay only for tokens used. Top up in USD via Stripe — credit never expires. Per-model rates are shown in the models table above.

Free trial
$0.20

On signup. Enough to test a few hundred chat turns on Doubao Lite.

Starter
$5–50

Stripe checkout. Single-card payment, no subscription. Receipt by email.

Volume
$100+

Higher rate limits on request. Contact us for invoicing.