🤔 Introducing APISIX AI Gateway – Built for LLMs and AI workloads. Learn More

Apache APISIX AI Gateway

Open-Source AI Gateway for LLMs and AI Agents

Use Apache APISIX as an open-source LLM gateway and proxy for model routing, load balancing, retries, fallback, token rate limiting, security, and observability.

20+
model providers
100+
gateway plugins
0
vendor lock-in

One gateway, two workloads

Manage API and AI traffic together

Keep the routing, security, observability, and operations model your teams already use while adding LLM traffic.

Apache APISIX

No vendor lock-in

Open-source data plane, open plugin model, and portable configuration for APIs and AI workloads.

100+

Gateway capabilities

Authentication, traffic control, observability, serverless, and AI plugins.

Open AI plugin ecosystem

Load balancing, fallback, token controls, RAG, prompt policies, moderation, and auditing are all available as open-source plugins.

AI plugin icons

Architecture

A control point between applications and models

Apache APISIX AI Gateway architecture

Built for production AI traffic

Reliability, control, and visibility at the gateway

Multi-LLM load balancing

Route across OpenAI, DeepSeek, Claude, Mistral, Gemini, and other providers with health checks and weighted balancing.

Token rate limiting

Control token consumption by Route, Service, Consumer, Consumer Group, or custom attributes in standalone and cluster deployments.

AI RAG

Connect enterprise knowledge to model requests at the gateway layer for grounded, context-aware responses.

Token observability

Track token usage through access logs and existing observability tools to control abuse and unexpected cost.

Retry and fallback

Use health checks, automatic retries, and fallback providers to keep AI applications available when an upstream model fails.

Prompt security

Apply prompt guards, decorators, templates, content moderation, logging, and auditing before traffic reaches a model.

Provider choice

Route to the model that fits each request

Use OpenAI, DeepSeek, Claude, Mistral, Gemini, self-hosted models, or a mix of providers without changing the application-facing gateway.

See the AI Gateway capabilities
Supported LLM providers