Skip to content

Transparent, Usage-Based Pricing

No black box. A voice agent is a stack — speech recognition, a language model, a voice, and a phone line. We show you the real cost of every layer, so you always know where your money goes.

Talk to us about a build

The real cost of every layer

Most platforms bundle everything into one padded per-minute number. We don't. Below are the exact per-unit rates Yaapi meters every call against, in the providers' own units — so you can see precisely what powers your agent.

LayerProvider & modelRate
Speech‑to‑textDeepgram Nova‑2$0.0077 / min
Language model
you choose per build
OpenAI GPT‑4o mini$0.15 / $0.60 per 1M tokens
DeepSeek Chat$0.27 / $1.10 per 1M tokens
Groq Llama 3.3 70B$0.59 / $0.79 per 1M tokens
Anthropic Claude Haiku 4.5$1.00 / $5.00 per 1M tokens
Text‑to‑speechElevenLabs Flash v2.5$0.055 / 1k chars
ElevenLabs Multilingual v2$0.11 / 1k chars
TelephonyInbound phone minutes$0.01 / min

Token rates show input / output. Provider rates are set by each vendor and change over time; these are the rates Yaapi currently meters every call against (as of August 2026). You pick the model that fits your quality and budget.

In practice, a typical conversation minute runs roughly $0.06–$0.10 at provider cost. Text-to-speech is usually the largest single component, so the exact figure depends on how much the agent talks and which model you run — we help you pick the stack that fits.

What Yaapi charges

The rates above are the underlying provider costs. Yaapi's own pricing is scoped to your build — every agent is custom-engineered for your business logic, not sold as a fixed tier. Tell us what you need and we'll put a number to it.

Want a number for your use case?

Talk to us