Bills without explanations
A total at the end of the month tells you nothing about what to fix.
Analytics
Every token, accounted for
Track usage by day and month to date, drill into individual requests, and see how much of your free allowance remains. No surprises at invoice time.
Daily detail
tokens and spend by day
Month to date
always know where you stand
Per-request truth
tokens, latency and price
The problem
What is slowing you down today
No per-request visibility
When latency or cost jumps, you cannot see which calls did it.
Allowances you cannot track
You only learn the free tier ran out when a charge appears.
Capabilities
Everything you need, nothing you don't
Last 30 days chart
Daily tokens and spend at a glance in the usage dashboard.
Daily detail table
Requests, tokens and price for each day.
Month-to-date totals
Running totals that match what will be invoiced.
Free allowance meter
See how much of this month's free tokens you have used.
Request history
Every call with model, tokens, latency, price, cache status and a short preview.
Numbers in every response
The same figures come back with each API call for your own observability.
Use cases
What teams run on it
01
Budget tracking
Watch spend against plan as features roll out.
02
Cost per feature
Separate keys make each integration's usage clear.
03
Latency investigations
Spot slow calls and the models behind them.
04
Cache effectiveness
See how much repeat traffic is served free.
How it works
From sign-up to production
- 1
Make requests
Every call is metered automatically.
- 2
Open Usage
See daily and month-to-date totals and your free allowance.
- 3
Drill into History
Inspect any individual request.
Control
Built so you stay in charge
Keys you control
API keys are shown once at creation and stored only as a hash. Revoke any key instantly from Settings.
Spend you can see
Every request carries its own receipt: tokens in, tokens out, latency and price. Nothing is billed that you cannot trace.
Limits you set
Per-account rate limits and a free monthly allowance keep experiments safe before they become production.
Data you decide on
You choose exactly what you send. Repeat prompts can be served from your cache, and cache hits are never billed.
For developers
One endpoint. Every model.
Send a prompt and a capability, or name a model. One bearer key, one small JSON body, and a full receipt on every response.
curl https://YOUR-DOMAIN/api/ainf/inference \
-H "Authorization: Bearer $AI_INFERENCE_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-1042" \
-d '{"prompt":"Summarise this ticket in one line","capability":"chat"}'Questions, answered
How current is the data?
Each call is recorded when it completes, so dashboards reflect your traffic as it happens.
Can I break usage down by feature?
Every response carries tokens and price, so you can tag and total them by feature or customer in your own systems.
Do the numbers match my invoice?
Invoices are built from the same metered usage you see in the dashboard.
Can I export my data?
Every response carries tokens, latency and price, so you can log them into your own systems as you go.
See where every token goes
Dashboards are live from your first request.