Skip to main content
A short answer for evaluators. The detailed breakdowns live in Call pricing, Agent pricing and Preferred models.

The short version

Voice AI

Transcription + LLM + text-to-speech. Covered by a flat per-minute rate as long as your agent uses preferred models.

Telephony

Charged per minute by the carrier, and it varies by country and provider. Billed by Bolna, or by your own provider if you bring your own account.

Platform fee

Bolna’s own per-minute component. See Call pricing for how the three parts add up.
Billing is usage-based and prepaid from your wallet. Larger top-ups move you to a lower effective per-minute rate.

What pushes the cost up

For a working method rather than a table, see Control cost per call.

What is not billed per minute

  • Agents themselves — see Agent pricing for how many agents a workspace can hold.
  • Concurrency — how many calls you can run simultaneously is an account setting, not a per-call charge. See Plan concurrency.

Next steps

Full pricing breakdown

Every component, with worked examples

Preferred models

What the flat rate includes

Control cost per call

Reduce spend without hurting quality