Leading AI Application Infrastructure

High-Speed AI Model
API Relay

Access massive domestic models through a unified, standard interface protocol. Host AI applications, efficiently manage token assets, and connect to the future.

View Integration Docs

Start now, connect to all major models in 5 minutes

Popular Apps Support

Full support for various tool ecosystem protocols

Claude Code Codex OpenCode More

POST /api/v1/chat/completions
Request
curl -X POST "https://ygw.ai/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 Dianming 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://ygw.ai/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 assist you?" }]
}],
"usage": { "total_tokens": 31 }
}

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

POST /api/v1/messages
Request
curl -X POST "https://ygw.ai/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://ygw.ai/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

Domestic Direct Access, Ultra-Low Latency

Deployed on Alibaba Cloud nodes, no proxy needed, high-speed domestic direct connection, average latency 50ms.

Avg Latency 50ms

Lower Cost, Pay-as-You-Go

Input/output token prices are about 30%–70% lower than official. Pay only for what you use, no minimum spending.

30%–70% Lower Than Official

Zero-Code Change, OpenAI Compatible

No SDK modifications needed, just change one line of base_url to integrate. Fully compatible with OpenAI API format.

Just Change base_url

99.9% SLA Guarantee

Intelligent routing and automatic failover, multi-node high-availability deployment, enterprise-grade stability guarantee.

Smart Routing · Auto Failover

MODEL PROVIDERS

All Major Providers Covered

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

Tencent Cloud

Zhipu AI

Qwen

DeepSeek

Doubao

Kling

Jimeng

MiniMax

Vidu

HappyHorse

QUICK START

3 Steps to Integrate in 5 Minutes

Register Account

Replace base_url

Replace base_url in your existing SDK with Dianming endpoint, no business code changes needed.

base_url = "https://ygw.ai/api/v1"

Start Calling

Call any model, pay by actual token usage, pay only for what you use.

USE CASES

Typical Use Cases

Agent

AI Agent Orchestration

Build complex AI Agent workflows, support tool calling and multi-turn conversations, flexibly orchestrate multi-model collaboration.

RAG

Smart Customer Service / RAG

Knowledge-base powered intelligent Q&A system, excellent Chinese understanding, precise retrieval-augmented generation.

Content

Content Generation / SEO

Low-cost bulk generation of long articles, marketing copy and SEO content, pay-as-you-go significantly reduces content production costs.

Research

Research / Data Analysis

Call reasoning models for data analysis and scientific computation, no need to build GPU clusters, elastic on-demand usage.

Ready to Simplify
Your AI Integration?

View Pricing

High-Speed AI ModelAPI Relay