Pricing and credits

How a call is priced

Calls are priced per minute, not per token. A call's charge is the per-minute cost of the providers it used, plus a flat platform fee, over the call's duration.

Per-minute is a deliberate choice. Per-token metering sounds more precise, but usage cannot be captured reliably for every provider - streaming models, some voices, and custom endpoints do not report it - which would force a per-minute fallback anyway and leave you with pricing that changes depending on which provider you picked. A single, predictable model you can quote to your own customers is worth more than false precision.

For current rates, see the pricing page and its calculator.

What you are charged for

A session's cost is broken down by component - transcriber, model, voice, and the platform fee - and shown on the session itself, so it is auditable rather than a single number.

Bring your own keys

When a provider runs on your own key, Glytos is not buying that provider for you, so it is not charged. The flat platform fee still applies to the call.

Credit

An organization runs on credit, and a new one starts with a welcome credit so you can build and test before paying anything.

Running low

Credit cannot go meaningfully negative, and calls are bounded rather than cut off mid-sentence without warning:

• A call is refused if the balance is below the minimum needed to start one.
• A call ends at the earliest of: the agent's own maximum duration, the platform's hard cap, and the point the remaining balance can pay for.

Top up

Top up from billing. An account must have a verified email before it can top up.