The Leading AI Application Foundation

High-Speed AI Model
API Gateway for China

Connect to a vast array of domestic models through a unified, standard API protocol. Power your AI applications, manage token assets efficiently, and connect to the future.

View Integration Docs

Get started now — connect to leading models in just 5 minutes

Works With Popular Apps

Full support for every major tool ecosystem

Claude Code Codex OpenCode More

POST /api/v1/chat/completions
Request
curl -X POST "https://api.aa.com.cn/api/v1/chat/completions" \
-H "Authorization: Bearer sk-****" \
-H "Content-Type: application/json" \
-d '{
  "model": "deepseek-v4-flash",
  "messages": [
    {"role": "user", "content": "Hello!"}
  ]
}'
Response
{
"choices": [{
  "message": { "content": "Hello! I'm the Dianming Token AI assistant. How can I help you?" }
}],
"usage": { "total_tokens": 27 }
}

              142 MS • 27 TOKENS • COST $0.00081
              STREAM • SSE
            

POST /api/v1/responses
Request
curl -X POST "https://api.aa.com.cn/api/v1/responses" \
-H "Authorization: Bearer sk-****" \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen3.7-max",
  "input": "Hello!"
}'
Response
{
"output": [{
  "type": "message",
  "content": [{ "text": "Hello! How can I help you?" }]
}],
"usage": { "total_tokens": 31 }
}

              168 MS • 31 TOKENS • COST $0.00093
              STREAM • SSE
            

POST /api/v1/messages
Request
curl -X POST "https://api.aa.com.cn/api/v1/messages" \
-H "x-api-key: sk-****" \
-H "Content-Type: application/json" \
-d '{
  "model": "deepseek-v4-pro",
  "max_tokens": 1024,
  "messages": [
    {"role": "user", "content": "Hello!"}
  ]
}'
Response
{
"content": [{
  "type": "text",
  "text": "Hello! I'm Claude. How can I help you?"
}],
"usage": { "output_tokens": 19 }
}

              203 MS • 19 TOKENS • COST $0.00114
              STREAM • SSE
            

POST /api/v1/v1beta/models/gemini-3.5-flash:generateContent
Request
curl -X POST "https://api.aa.com.cn/api/v1/v1beta/models/gemini-3.5-flash:generateContent" \
-H "Authorization: Bearer sk-****" \
-H "Content-Type: application/json" \
-d '{
  "contents": [{
    "parts": [{"text": "Hello!"}]
  }]
}'
Response
{
"candidates": [{
  "content": {
    "parts": [{ "text": "Hello! I'm Gemini. How can I help you?" }]
  }
}],
"usageMetadata": { "totalTokenCount": 24 }
}

              156 MS • 24 TOKENS • COST $0.00072
              STREAM • SSE
            

WHY US

Why Choose Dianming Token

Direct Domestic Connection, Ultra-Low Latency

Deployed on Alibaba Cloud nodes, no proxy required, high-speed direct connection in China with an average latency of 50ms.

Average latency 50ms

Lower Cost, Pay As You Go

Input and output token prices are roughly 30%–70% lower than official rates. Pay only for what you use, with no minimum spend.

Roughly 30%–70% lower than official

Zero-Modification Integration, OpenAI-Compatible

No SDK changes required — just update the base_url in one line. Fully compatible with the OpenAI API format.

Just change base_url

99.9% SLA Guarantee

Smart routing and automatic failover with multi-node high-availability deployment for enterprise-grade stability.

Smart Routing · Automatic Failover

MODEL PROVIDERS

All Major Providers Covered

Access 100+ large models through a single API endpoint, covering all major domestic and international providers.

Tencent Cloud

Zhipu AI

Qwen

DeepSeek

Doubao

Kling

Jimeng

MiniMax

Vidu

HappyHorse

QUICK START

Three Steps, Live in 5 Minutes

Create an Account

Replace base_url

Replace the base_url in your existing SDK with the Dianming Token endpoint — no changes to your business code.

base_url = "https://api.aa.com.cn/api/v1"

Start Calling

Call any model and pay based on actual token usage — pay only for what you use.

USE CASES

Typical Use Cases

Agent

AI Agent Orchestration

Build complex AI agent workflows with tool calling and multi-turn conversations, flexibly orchestrating multi-model collaboration.

RAG

Intelligent Customer Service / RAG

Knowledge-base-driven Q&A with excellent Chinese comprehension and precise retrieval-augmented generation.

Content

Content Generation / SEO

Batch-produce long-form content, marketing copy, and SEO articles at low cost, with pay-as-you-go pricing significantly cutting content production expenses.

Research

Research / Data Analysis

Use reasoning models for data analysis and research computing without building your own GPU clusters — scale elastically on demand.

Ready to simplify
your AI integration?

View Pricing

High-Speed AI ModelAPI Gateway for China