Managed hosting
We run Core for you, with upgrades, backups and monitoring included.
Platform overview
One open engine under every AI app
OpenUno Core is the gateway and router. OpenUno Chat is the free app built on it. Enterprise and the API are the paid parts, for company teams and products.
Products
Free for people, paid for company teams and the API
Early accessDistribution
OpenUno Chat
Free multi-model AI for everyone. Smart routing picks a good model for each question and keeps the cost down, so free can stay free.
- Several models behind one chat
- Smart routing by quality, cost and speed
- Fair free limits, or bring your own keys
- In the browser, or as a desktop app
In designDeveloper adoption
OpenUno Core
The open-source engine underneath: an AI gateway, model router, tools, connectors, observability and usage controls you can run on your own servers.
- Standard chat-completions API
- Policy-based model routing
- Budgets, rate limits and keys
- Usage and cost observability
PlannedRevenue
Enterprise & API
The only paid parts. Enterprise gives company teams a shared, governed workspace where company data never trains models. The API is pay per use for developers and products.
- Team workspaces, SSO and roles
- Company data isolated, never used for training
- Audit trail and reports
- Pay-per-use API with budgets and keys
Architecture
Chat, SDKs and apps → gateway → router → models
An event and data layer runs beside the request path and feeds analytics and governance.
OpenUno ChatFree multi-model chat
SDK & APIStandard chat-completions
Your appsAgents, tools, schools
AI GatewayKeys · identity · budgets · rate limits
Model RouterQuality · cost · latency · policy
Open-weight modelsSelf-hosted or managed
Premium modelsFor the hard questions
Your own keysBilled to you
Event & data layerUsage, cost and consent events
AnalyticsAggregated usage and cost
GovernanceAudit trail and privacy controls
Step 1 of 4
Connect
Plug in the models you want: open-weight models, premium models or your own keys. One API in front of all of them.
- Bring your own keys
- Standard API
- Self-host or managed
Step 2 of 4
Route
The router chooses a model for every request by quality, cost, latency and your policies, with fallbacks when a provider is busy.
- Quality, cost and latency
- Policy rules
- Automatic fallback
Step 3 of 4
Govern
Budgets, identity, rate limits, consent and audit sit in the gateway, so every app inherits them without extra code.
- Budgets and limits
- Identity and roles
- Consent and audit
Step 4 of 4
Build
Ship chat, agents and apps on top: SDKs, tools and connectors, with usage and cost visible from the first request.
- SDKs and tools
- Connectors and agents
- Usage analytics
Enterprise · Planned
A governed workspace for company teams
For company teams that want OpenUno managed, with their data isolated and never used to train models.
Workspaces and roles
Organisations, teams and classes, with enterprise single sign-on.
Reports
Usage, cost and adoption by workspace, team and model tier.
Governance and audit
Policies, consent records and an audit trail you can export.
SLA and support
Agreed availability, response times and a named contact.
Private deployment
Your cloud or your data centre, in your jurisdiction.
UnoEnterprise is planned. Tell us what your organisation needs and you will help decide what ships first.
Start free. Grow when you need to.
Start free in the browser, or help shape the open-source core. Schools, partners and teams: we would love to hear from you.