Hajiyun API 🐾
Ultra-low latency, transparent LLM relay. Native Claude 4.6, Gemini 3.8 & OpenAI streaming. Optimized for SillyTavern, roleplay, and developer agents.
# 1-Minute Quickstart (OpenAI Compatible)
curl https://hajiyun.top/v1/chat/completions \
-H "Authorization: Bearer sk-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.8-flash-high",
"messages": [{"role": "user", "content": "Hello!"}]
}'
curl https://hajiyun.top/v1/chat/completions \
-H "Authorization: Bearer sk-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.8-flash-high",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Plug & Play Integration
Standard OpenAI-compatible format. Seamless 1-minute integration with SillyTavern, NextChat, Chatbox, and Python/Node.js SDKs.
Rock-solid Availability
Enterprise multi-egress intelligent failover, residential IP pool, and real-time Relay Pulse monitoring. 99.9% uptime SLA.
Transparent Pricing
Pure USD pay-as-you-go billing with real token tracking. No hidden markups, instant testing quota upon sign up.