Opaque pricing
Credits, tiers and multipliers make it impossible to know what a call costs.
Billing
Pay for tokens, not surprises
Start free every month. Beyond the allowance, pay per token at the price listed for each model, see the price on every response, and settle metered usage every 30 days.
Free allowance
every month, on every account
Price before you call
listed per model in the catalog
Cache hits free
repeats cost nothing
The problem
What is slowing you down today
Big bills, late
A month of usage lands in one invoice, long after you could have responded.
Paying for retries
The same answer billed twice because a client retried.
Capabilities
Everything you need, nothing you don't
Free monthly allowance
Every account gets free tokens each month, applied before metered pricing.
Per-token pricing
Input and output prices are shown for each model before you call it.
Exact price per response
Every response reports price_micros, the exact charge for that call.
Cache hits not billed
Repeated identical prompts inside the cache window cost nothing.
Idempotent metering
Send an Idempotency-Key and a retried request is metered once.
Monthly usage invoices
Metered usage is invoiced every 30 days, emailed to you, and paid online.
Use cases
What teams run on it
01
Prototyping
Build on the free allowance before you spend anything.
02
Usage-based products
Pass per-call prices through to your own customers.
03
Budget-conscious teams
Short invoice cycles keep spend close to usage.
04
Finance reporting
Dashboards and invoices from the same metered data.
How it works
From sign-up to production
- 1
Start free
Your monthly allowance is applied automatically.
- 2
Add a payment method
Set up billing through the hosted checkout when you are ready.
- 3
Pay as you go
Metered usage is invoiced every 30 days.
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
What is free?
A monthly token allowance on every account, plus every cached response.
How do I know what I will pay?
Prices are listed per model before you call, and each response reports its exact price in micros.
How often am I invoiced?
Metered usage is invoiced every 30 days, emailed to you, and paid online.
Am I charged for failed requests?
No. You pay for calls that succeed, at the price of the model that served them.
Start free. Scale on clear prices.
No commitment to begin. Your allowance resets every month.