GLM · Qwen · DeepSeek · Kimi

Chinese AI Models, One API

Call GLM, Qwen, DeepSeek, and Kimi through one OpenAI-compatible key — no Chinese phone number, no mainland account, no separate vendor consoles. Pay in USD or your local payment method.

Get your API key See live pricing

GPT · Gemini · Claude · DeepSeek · Seedance — one key, one invoice · no credit card to start

Output price vs official

DeepSeek V4 Flash / 1M tokens	$0.07	$0.14
Qwen 3.7 Plus / 1M tokens	$0.24	$0.40
GLM 5.2 / 1M tokens	$0.56	$1.40

* Illustrative pricing — see the flatkey pricing page for live rates.

One key for every Chinese frontier model

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://router.flatkey.ai/v1",
    api_key="YOUR_FLATKEY_KEY",
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

curl

curl https://router.flatkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $FLATKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

No mainland account needed

Skip Chinese phone verification, local ID, and mainland billing accounts. Sign up with Google or GitHub and start calling models.

GLM, Qwen, DeepSeek, Kimi

The Chinese frontier models behind one endpoint — compare them against GPT, Gemini, and Claude by swapping a model id.

Pay in USD or local methods

Top up in USD with international cards or local payment methods. No RMB accounts or cross-border transfers.

OpenAI-compatible

Your existing OpenAI SDK works as-is: change base_url and api_key, keep everything else.