AISIX AI Gateway

Put one stable API contract in front of your AI providers

AISIX AI Gateway gives platform teams one gateway boundary for LLM and AI-agent traffic. The Rust-native gateway keeps provider credentials, model aliases, routing, failover, rate limits, caching, guardrails, and observability behind a stable API contract. Choose AISIX OSS to operate the Apache-2.0 gateway directly, AISIX Enterprise to run the control plane in your infrastructure, or AISIX Cloud to use an API7-hosted control plane.

Get started View supported endpoints

Start AISIX Enterpriselocalhost:8080

curl -fsSL https://run.api7.ai/aisix-self-hosted/quickstart | bash

# Starts the control plane and dashboard
# Dashboard: http://localhost:8080

How requests flow

Applications call AISIX first. AISIX authenticates the caller, resolves the model alias, applies policy, and forwards the request to the selected provider.

ApplicationsApps, agents, and servicesSend OpenAI-compatible requests with gateway-issued caller API keys.

AISIX gateway boundaryStable contract, controlled provider access

AISIX keeps client traffic on one API shape while resolving the provider-side target for each request.

Authenticate callerResolve model aliasApply limits, cache, and guardrailsSelect provider route

ProvidersOpenAI, Anthropic, Bedrock, Vertex, AzureReceive provider-authenticated requests from the gateway.

Provider responses return through AISIX using the same client-facing contract.

What changes when AI traffic goes through an AISIX gateway

Application teams keep calling a familiar API. AI platform teams move provider credentials, model aliases, routing, and policy into one operator-managed gateway. AISIX Enterprise and AISIX Cloud each add centralized usage and budget controls.

AccessCaller API keys and model allowlistsAuthenticate applications and decide which model aliases each key can use.

ProvidersCentralized upstream credentialsKeep provider keys, base URLs, and adapter details out of application code.

RoutingStable aliases with failoverExpose one model name while AISIX selects target models behind it.

PolicyLimits, cache, guardrails, telemetryApply AI-specific controls and usage visibility before requests leave your gateway boundary.

Why AISIX AI Gateway if you already use APISIX or API7 Gateway?

APISIX and API7 Gateway can add AI behavior to regular gateway routes through AI plugins. That path fits teams whose main workload is API traffic and whose AI calls are part of a broader API gateway deployment.

AISIX AI Gateway is for teams whose main workload is AI traffic. It manages provider keys, model aliases, caller API keys, routing, and policy through AI-specific resources, and emits AI usage telemetry. AISIX Enterprise and AISIX Cloud each add centralized usage views and budgets.

Why AI Gateway explains why production AI traffic benefits from a purpose-built gateway and when an existing API gateway remains the better fit.

APISIX

Add AI features to existing API routes.Use AI plugins when your existing API gateway route is the natural place to call or transform AI services.

AISIX AI Gateway

Run AI traffic through a dedicated gateway domain.Use AISIX AI Gateway when applications should call stable model names while an AI platform team owns provider keys, routing, policy, and usage visibility.

Choose Your Next Path

Start with the product that matches who should operate the control plane. All three products keep the gateway and live AI traffic in your infrastructure.

AISIX OSS

Run AISIX OSSConfigure AISIX directly with a resources file and send your first request.

AISIX Enterprise

Operate the control plane yourselfDeploy the customer-hosted control plane, attach a gateway, and configure a model.

AISIX Cloud

Use the API7-hosted control planeManage gateways centrally without operating the control plane.

Production

Prepare the runtime for productionReview deployment, security, health, metrics, and troubleshooting guidance for production gateways.