The Unified Gateway for LLMs
One API to access 250+ models from 8+ providers. Smart routing, built-in reliability, and enterprise-grade security.
Terminal
curl https://api.wuguhub.com/v1/chat/completions \
-H "Authorization: Bearer hiai-xxx" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-4o", "messages": [...]}'250+
Supported Models
8+
Providers
4
Routing Modes
99.9%
Uptime
Everything you need to manage LLMs
One API for Any Model
Access all major models through a single, unified interface. OpenAI SDK works out of the box.
Smart Routing
4 routing modes: single, fallback, load-balance, and conditional. Intelligent model selection based on your rules.
Built-in Reliability
Auto-retry, semantic caching, circuit breaker, and rate limiting. Keep your applications running smoothly.
Enterprise Security
40+ guardrail rules, PII masking, RBAC permissions, and full audit logging. Protect your data and users.
LLM Providers
Manage your AI model providers
OpenAI
Anthropic
Google
Qwen
Zhipu AI
MiniMax
Moonshot
Ollama