Retell AI pricing: estimate your configured agent and phone usage
A guide to reading Retell pricing, selecting the right configuration and reconciling calls, transfers and recurring costs.
Table of Contents▼
Retell's pricing page presents a configurable voice-agent estimate rather than one universal price for every assistant. The selected model, voice, telephone arrangement and enabled options determine the relevant quote. Use the official calculator and terms for your configuration.
Start with the call you intend to run
Record whether the assistant handles inbound or outbound calls, the destination countries, expected duration, model and voice choices, and any optional features. A quote based on a different model or a browser session will not necessarily describe your telephone workload.
Separate recurring items such as phone numbers from usage. Include direct carrier bills if your telephone arrangement places them outside the platform invoice.
Build a transparent estimate
| Component | Input to collect |
|---|---|
| Voice agent | Selected configuration and billable duration |
| Telephony | Inbound/outbound route and each connected leg |
| Add-ons | Only the options actually enabled |
| Recurring resources | Numbers and contractual commitments |
| Operations | Integration infrastructure and human recovery work |
Avoid copying an old screenshot into a permanent budget. Save the dated quote and configuration used for the estimate, then compare them with the actual account statement after the pilot.
Pay attention to transfers and silence
A handoff changes which parts of the service remain active. Ask how AI usage and telephone usage are billed before, during and after transfer, particularly when legs overlap. Likewise, confirm how connected silence or hold time is treated rather than assuming that only spoken seconds count.
These questions matter even when most calls are short: a small number of unusually long calls can dominate a pilot's expense.
Example of a useful pilot report
For each representative call, record its identifier, connected duration, intended result, action evidence, transfer outcome and settled expense. Add a separate field for human follow-up required because the assistant failed.
Then calculate total expense per verified useful result. If two configurations use different voices or models, state that explicitly; the difference cannot automatically be attributed to the platform itself.
Comparing Retell with Burki
Burki is another candidate to evaluate through the same scripts and complete accounting. Compare current Burki pricing with a complete Retell configuration, not with one isolated fee from either product.
If you are already operating successfully on Retell, include migration effort, number routing and history retention in the decision. A small apparent usage saving may not justify disrupting a working service. The Retell alternatives guide covers that operational comparison, while the cost worksheet keeps the arithmetic consistent.
Ready to try Burki?
Create an assistant and check your available browser practice allowance.
Create your assistantTrial eligibility and available practice are shown in your workspace.