Billing & consumption
wylon uses pay-as-you-go billing metered per token. This page explains how usage is measured, how charges accrue, and how to review your consumption.
Pricing model
Every inference request is billed on two dimensions:
- Input tokens — everything you send: the prompt, system message, tool definitions, and prior turns.
- Output tokens — everything the model generates, including tool-call arguments and reasoning tokens.
Rates are per-million tokens and vary by model. Batch jobs receive a discount on top of the standard rate. See the pricing page for current rates.
calculate
Token counts returned in the
usage field of each response are authoritative —
they are what you will be charged for. Cached prefix tokens (when eligible) are billed at a
reduced rate and appear as cached_input_tokens.
Usage dashboard
Dashboard → Account management → User Center → Usage statistics breaks down consumption by model, API key, and day, with export support.
Invoices & receipts
To view receipts or issue invoices, go to Dashboard → Billing → Invoice management.
FAQ
Are failed requests billed?
No. Responses with a 4xx or 5xx status are not charged. Timed-out streams are billed only for tokens actually produced.
Are batch jobs billed differently?
Batch jobs are still billed per token but receive a discount compared with real-time calls. See Batch inference.
Can I increase my usage limits?
Contact our sales team to request a higher usage quota.
