06 · Enterprise AI control layer

AISIX AI Gateway

AISIX is an AI-native gateway built for model and agent traffic. It gives every application one controlled way to reach models: stable model aliases, central credentials, routing, limits, guardrails and usage telemetry in a single control plane.

One gateway · many models · centrally controlled. AISIX is part of the DOME CLOUD AI infrastructure practice. It is not Apache APISIX or API7: AISIX handles AI traffic, while APISIX and API7 handle general API traffic.

Why AISIX

AI is already in the company. The control layer usually is not.

Most teams adopted AI faster than the organisation could govern it. AISIX sits between your applications and AI providers, so every request is authenticated, routed, limited and recorded in one place.

Point-to-point no shared policy
HR AppFinanceCRMCoding agents
Provider AProvider BProvider CProvider D

Each application holds its own provider key, policy and logs.

One control plane one policy plane
HR AppFinanceCRMCoding agents
AI Gateway auth · routing · policy · telemetry
Provider AProvider BProvider CProvider D

Applications call aliases. AISIX holds the keys, applies policy and records usage.

Five control problems AISIX closes

01

Fragmented credentials

Every team stores its own provider keys and settings.

Central caller keys and provider credentials, scoped by model and tool.

02

Vendor lock-in

Changing a model means changing every application.

Stable model aliases, so applications stop hard-coding providers.

03

Uncontrolled spend

Token usage and provider bills are spread across teams.

Usage and budget controls per caller, where the edition supports it.

04

Inconsistent policies

Each application has its own limits, guardrails and logs.

One policy plane for traffic that passes through the gateway.

05

Limited visibility

Requests, latency, errors and AI usage are scattered.

Usage events, metrics and audit history in one place.

Is this you?

You probably need AISIX if...

Most companies answer yes to at least two.

Book a readiness assessment
  • 01 Your teams already use more than one AI provider.
  • 02 More than one application holds its own provider key.
  • 03 You need AI spend visibility by team or application.
  • 04 You need consistent limits and guardrails.
  • 05 Agents or tools can take actions with AI.
  • 06 You need audit evidence for AI usage.

Two or more yes? Start with an AISIX readiness assessment.

What we deliver

Three services, delivered end to end

Scope it precisely, deliver it completely.

01

Access & credentials

Caller keys, model and tool permissions, and provider credentials held centrally instead of inside every application.

  • Caller keys
  • Model access
  • Central provider keys
02

Model routing

Stable model aliases with routing and failover, so you can change providers without changing application code.

  • Aliases
  • Failover
  • Provider choice
03

Policy & visibility

Rate limits, budgets and guardrails per caller, with usage events, metrics and audit history across AI traffic. Budget controls depend on edition.

  • Rate limits
  • Budgets*
  • Telemetry
Inside the control plane

See one request move through AISIX.

Switch between the four controls to see what AISIX does before a model provider is called. This is a simulation, not live traffic.

AISIX Gateway Simulation
1The app sends a request
2AISIX checks access and policy, then routes it
3The provider returns a response
App
HR App hr-analytics
app key
Model alias
summary-standard

A stable name the app calls. The provider behind it can change.

AI Gateway control plane
  • Authenticate
  • Authorize
  • Apply controls
  • Route
  • Observe
  • Return
AI traffic Policy applied
Result
Allowed Simulation

The application never holds a provider key.

Provider keys
ABC
Held by AISIX
  • App key verified
  • Provider keys stay inside AISIX
Simulation only. No live traffic or data. AISIX AI Gateway
Editions & deployment

One gateway. Three ways to run the control plane.

In every edition the gateway runtime stays in your environment. The difference is where the control plane lives and how much management is built in.

Your environment
Apps & agents
Enterprise appsAI agentsCoding tools
AI Gateway
AuthenticationModel aliasesLimits & guardrailsUsage telemetry
Models · MCP · A2A
Public modelsPrivate modelsMCP toolsA2A agents

AISIX OSS

Open source

Teams that operate the gateway themselves.

Gateway runtime
Customer-operated
Control plane
Not included
Configuration
Declarative / self-managed
Usage, budgets & audit
Added separately

AISIX Enterprise

Self-hosted control plane

Organisations that need to run the control plane themselves.

Gateway runtime
Customer-operated
Control plane
Customer-hosted
Configuration
Dashboard + Admin API
Usage, budgets & audit
Built in, by edition

AISIX Cloud

Hosted control plane

Teams that want a hosted control plane.

Gateway runtime
Customer-operated
Control plane
API7-hosted
Configuration
Dashboard + Admin API
Usage, budgets & audit
Built in, by edition

Availability, edition and commercial terms are confirmed during the assessment.

AISIX · Assessment

Not sure which edition fits?

Start with a short assessment, or prove it with a PoC against a real use case.

01 Assess Inventory, architecture and edition fit.
02 PoC One or two real use cases on AISIX.
03 Rollout Policy, training and production operations.
AISIX® · AI Gateway

AI traffic is different.

AISIX sits beside your existing API gateway. One controls AI and agent traffic; the other keeps handling general APIs.

Traditional API Gateway

HTTP / API

Auth and routing for REST, GraphQL and internal services, with plugins, rate limits and service management.

  • HTTP / API traffic
  • Plugins and rate limits
  • REST, GraphQL, internal services

AISIX AI Gateway

AI / agents

A gateway purpose-built for model and agent traffic: model aliases, provider credentials, AI-specific routing and telemetry.

  • AI / agent traffic
  • Model aliases and provider keys
  • Guardrails, MCP / A2A where supported
Governance boundary

A gateway controls traffic. Governance covers the organisation.

AISIX enforces policy on every AI request that passes through it. Identity, data, cost and incident response still need to connect around it.

AI Gateway

AISIX enforces

  • Caller access
  • Model aliases and routing
  • Limits and guardrails
  • Usage telemetry
Gateway boundary
Connect around it
01

IAM & access

Joiner, mover, leaver and service identities

02

Data & privacy

Classification, DLP and application security

03

AI FinOps

Cost allocation and procurement

04

SIEM & response

Audit retention, detection and incident response

05

Resilience

Application resilience, recovery and BCP

You cannot govern what you cannot see.

AISIX makes AI traffic visible. The surrounding controls make it accountable.

How to start

A 90-day path, not a big-bang rollout.

Start with one or two real use cases. Prove control before scaling the programme.

Days 1 to 30 01

Assess and design

Inventory AI usage and risk, map data and identity requirements, and choose pilot applications.

  • AI usage and risk inventory
  • Target architecture
  • PoC plan
Days 31 to 60 02

Prove it

Stand up AISIX, connect one or two applications and providers, and test allowed, denied and failure paths.

  • AISIX environment
  • Verified PoC
  • Decision log
Days 61 to 90 03

Govern and scale

Write policies and operating procedures, add budget and audit controls, train the team, and plan the production rollout.

  • AI policies
  • Budget and audit controls
  • Production rollout plan
Book an AISIX assessment or PoC Read the infrastructure deck Scope and timeline depend on the organisation.
Why it works

Built to hold up in production

One control plane

Applications stop holding provider keys and per-app policies.

Switch models safely

Move traffic between providers at the alias, not in code.

See the spend

Token and usage visibility by caller, team or application, by edition.

Built for agents

MCP tools and A2A agents connect through the gateway where supported.

AISIX ≠ Apache APISIX ≠ API7

AISIX handles AI and agent traffic; Apache APISIX and API7 handle general API traffic. They are designed to run side by side, connected through shared identity and policy.

Read the AI infrastructure deck
Start a conversation

Ready to raise the ceiling on your platform?

Tell us what you're building. We'll assess it and propose the right approach, and the first conversation is free.

Messenger · m.me/domecloud.io