Skip to main content
Testing an agent bills at the same rates as production. There’s no separate test tier and no free testing sandbox, so a message or a minute spent testing costs what it would on a live call. Plan test usage like any other usage, and check the Retell pricing page for current rates.

​
How testing is billed

​
Text testing

The Playground, simulation testing, and batch testing run in text and bill per message, at the chat rate for the model you select. Rates range from roughly 0.001to0.001 to 0.05 per message depending on the model, so a cheaper model keeps iteration inexpensive. See the pricing page for the per-model rates. Two things that add up:
  • The simulated user also bills. In AI Simulated Chat, the model that plays the user bills per message too.
  • Batches multiply. A batch bills every case on every run, with no discount. Running 20 cases three times each bills 60 runs.

​
Voice testing

Web call testing and phone call testing place a real voice call and bill per minute, at the same rate as a production call: voice infrastructure, text-to-speech, and the LLM add up to roughly 0.07to0.07 to 0.31 per minute depending on the model and voice.
  • Phone testing adds telephony (about 0.015perminuteforaRetellnumber)andrequiresa[phonenumber](/deploy/purchase−number).Retellnumberscost0.015 per minute for a Retell number) and requires a [phone number](/deploy/purchase-number). Retell numbers cost 2.00 per month.
  • Web testing has no telephony line, since it runs in the browser.
Because a voice minute costs far more than a text message, run most of your checks in text simulation and reserve web or phone calls for final validation.

​
Conductor

Having Conductor generate test cases bills per Conductor request, and your account needs credits before Conductor runs. Any simulations Conductor runs on your behalf bill as normal per-message simulation runs. Check Billing → Usage for the exact amount.

​
Free allowances

  • $10 in free credits when you sign up.
  • 20 free concurrent calls.
  • AI QA: the first 100 minutes are free, then $0.10 per minute. See AI QA.
There’s no separate free tier for testing beyond these, so treat test usage as billable.

​
See also