Rapid AI Gateway Integration LLM API AI Agent LLM API
Production-grade AI Gateway
Open-source AI Gateway for Agent development and LLM API management
Free open-source and commercial cloud editions for models, tools, and MCP Servers
👋 Choose Your Solution
Or try the online Demo Try Open Source
News
One Higress for Three Types of AI Traffic
Connect model APIs, MCP tools, and Kubernetes inference workloads through one gateway
AI Apps & Agents One entry point
Higress AI Gateway
ONE GATEWAY LLM Gateway Model API governance
Unified APIsToken control
Model APIs
MCP Gateway Tool-call governance
MCP proxyTranslation
Tools & MCP Servers
Model Gateway Gateway API Inference Extension
InferencePoolEndpoint Picker
Inference Workloads
Model APIs
Tools & MCP Servers
Inference Workloads
Scenario Experience
Provides two channels: open source version and commercial product, one-click experience of AI application scenarios.
Multi-model Proxy
Learn Details The AI ​​gateway can forward requests from external calls to different large models to the corresponding internal large models through a unified call method, making backend model scheduling more flexible; Higress.ai supports unified protocol conversion for 100+ common models and supports model-level Fallback.
Application Protection
Learn Details The AI ​​gateway can protect data security when interacting with large models. On the one hand, it protects the privacy of data input to external models, and on the other hand, it filters content for data output to users.
AI Cache
Learn Details The AI ​​gateway supports precise caching and semantic caching of inference result contexts, saving Tokens and reducing latency for common similar/repeated questions, thereby improving the calling experience.
Token Management
Learn Details The AI ​​gateway can track the number of Tokens used by large models and limit them when consumers use excess, thereby better managing the user quota for calling AI applications and providing data support for Token usage analysis.