Per-request cost
Model, tokens and cost on every call, grouped by app, team and person.
Cost control · In design
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.
The problem
Why this matters
AI bills arrive at the end of the month, split across providers, with no way to tell which team, app or feature spent what.
Where it standsIn design This is part of OpenUno Core. We will say here when it ships.
How OpenUno helps
How it works
Budgets that hold
Monthly or daily caps per key or workspace. At the limit you choose: block, or downgrade to a cheaper lane.
Spend by tier
Watch the share of premium spend fall as routing sends routine work to smaller models.
Related
More capability solutions
AI gateway
A single, standard API for every model you use, with keys, identity, budgets and limits applied in one place.
Read moreModel routing
The router weighs quality, cost, latency and your policies, picks a model per request and falls back when a provider is busy.
Read moreBring 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.
Read moreAI that belongs to everyone.
Start free in the browser, or help shape the open-source core. Schools, partners and teams: we would love to hear from you.