Skip to main content
Agents cost $0.06 per minute of conversation, with a small number of add-ons for telephony and token-billed models. Every account starts with a $5 trial balance, and everything after that is charged against your API credit.

​
Rates

​
Per-session charges

These charges apply while a web session or phone call is running. Usage is counted per second. A plus sign marks a charge on top of the conversation rate. Calls on imported SIP numbers and WhatsApp calls carry no phone surcharge and no transfer fees. They bill like web sessions.

​
Transfers

When the agent transfers a phone call to a person, the conversation rate and phone surcharge stop, and the rest of the call is billed at a transfer rate instead:

​
Monthly fees

These charges apply whether or not your agent takes any calls. Imported SIP numbers and WhatsApp Business numbers carry no rental.

​
LLM models

The LLM your agent runs is chosen in the Builder. The basic models are:
  • Gemini 3.5 Flash Lite
  • GPT-5.6 Luna
  • Gemma 4 26B
Every model has a per-token cost. For now the conversation rate covers it for the basic models as a promotional offer, so they carry no separate charge. Every other model is billed on token usage. Prices are expressed in USD per 1 million tokens, with separate rates for input tokens, output tokens, and cached input. These rates are determined by the LLM providers and may change. Refer to the provider’s documentation for current pricing. What a minute costs on such a model therefore depends on your agent: how long the system prompt and retrieved knowledge are, how much conversation history the model re-reads on every turn, how often it is called, and how verbose its replies are. The Builder shows an estimated per-minute figure next to each token-billed model, computed from your current prompt and typical agent behavior. The estimate does not account for prompt caching, and actual charges are based on token usage. After a conversation, each message in the dashboard’s conversation view shows its model requests and token cost. A custom LLM endpoint carries no LLM charge.

​
Simulation tests

A Simulation test has the agent talk to a simulated user in text, then an LLM judge scores the conversation. There is no conversation rate. Each run that ends in Pass or Fail is charged:
  • A platform fee of $0.003 per agent reply. A fixed first message is spoken as written and is not counted, a generated one is.
  • The tokens of the agent, the simulated user, and the judge, each at the rate of the model it ran on. An agent on a custom LLM endpoint carries no charge for its own tokens.
A run that ends in Error is not charged, and every repeat of a test is a run of its own. Single Turn and Tool tests are free. With no conversation rate to cover them, the basic models are billed on their tokens in Simulation tests. Prices are in USD per 1 million tokens: The other models are billed at the same rates as in conversations. The result of each run shows what it was charged, and the Agents billing page itemizes the platform fee and each participant’s tokens.

​
Outbound destinations

The standard phone surcharge applies to inbound calls and most outbound calls. Outbound calls to the destinations below replace it with a rate that depends on the number dialed: The countries purchased numbers can call are listed under allowed destinations.

​
Trial balance

Every account starts with a one-time $5 trial balance, about 60 minutes of conversation at the base rate. It pays for real usage at the normal rates:
  • Every charge draws on it first: web sessions, phone calls and their surcharges, transferred call time, number rental, LLM tokens on token-billed models, and Simulation test runs. Only what the trial balance does not cover is charged to your API credit.
  • A session can start on any model, including token-billed ones, as long as the trial balance or your API credit is above zero. The same goes for running Simulation tests.
  • Preview calls in the Builder are free on every LLM, including token-billed ones, and never draw on the trial balance.
  • The Agents billing page shows how much of the trial balance is left, and the Agents home page shows it as a usage meter.

​
Billing

Usage is charged to your API credit, the same prepaid balance as the Fish Audio speech APIs. Sessions are charged when they end, Simulation test runs when they finish, and number rental is charged daily. Every charge is listed on the Agents billing page.

​
Examples

​
Going further

Quickstart

Create an agent and talk to it on the trial balance.

Phone numbers

Buy or import a number and bind it to an agent.

Transfers

Cold and warm transfers to a human.

Custom LLM

Run your own LLM endpoint at the base rate.