Find where OpenUno fits

AI gateway

One gateway in front of every model

A single, standard API for every model you use, with keys, identity, budgets and limits applied in one place.

Model routing

The right model for every request

The router weighs quality, cost, latency and your policies, picks a model per request and falls back when a provider is busy.

Cost control

See and cap what AI costs

Every request is logged with its model, tokens and cost. Budgets stop spend before it happens, not after the invoice.

Bring your own keys

Already have a contract with a model provider? Plug its key in and the router treats it like any other lane, billed to you.

Governance & audit

Governance that every app inherits

Audit trail, retention rules, consent and privacy controls live in the gateway, so each new app is governed from its first request.

Connectors & agents

Connectors and agents

Give models safe access to the tools and data they need, with the same identity and audit as every other request.

By audience

How OpenUno fits who you are.

For developers

Build on open infrastructure

Self-host the open-source core, or use the managed cloud. Either way: one API, routing, budgets and usage data from the first request.

For enterprise

AI across the company, under control

Managed or private deployment, single sign-on, roles, audit and an SLA, on the same open core your developers already use.

For the public sector

AI for public services

Open source you can inspect, deployment where your rules require it, and data principles written before the first request.

By outcome

What you get when it is running.

Lower AI cost

Lower the cost of every answer

Most questions do not need the most expensive model. Routing sends them to one that answers well for less.

AI readiness

Get your organisation AI-ready

Start with free chat for everyone, add workspaces and policies as you learn, and move to governance when you scale.