Vapi
Developer-first voice agent platform at $0.05/min platform fee plus model pass-through
What is Vapi?
Vapi is a developer platform for building real-time voice AI agents that handle inbound and outbound phone calls, with sub-500ms latency and bring-your-own-key support for STT, LLM, and TTS providers. Its pricing strategy is transparent: Vapi charges a flat $0.05/minute platform fee and passes through model and telephony costs at provider rates, which means your effective per-minute cost is highly dependent on which models you choose.
Voice agents and conversational AI platforms for calls, qualification, scheduling, support, and audio workflows.
See the full Voice AI guide to compare more tools, buyer criteria, and related workflows.
Use cases to evaluate
Build an outbound sales SDR agent that dials leads, qualifies on a script, and books meetings into Calendly
Replace an after-hours support IVR with a voice agent that can transfer to a human when confidence drops
Run patient appointment reminder calls with HIPAA mode enabled and pass-through Twilio telephony
Spin up a tenant-isolated voice agent per customer using BYO LLM keys so model costs flow back to them
Fit to evaluate
Voice AI startups and YC-stage teams building branded voice products on top of best-of-breed models
Engineering teams that want STT, LLM, and TTS provider flexibility instead of a black-box bundle
Agencies deploying voice agents per client with bring-your-own-key cost attribution
High-volume call operations where annual Scale contracts unlock committed-volume per-minute rates
Business fit
Right for you if you have engineering capacity, want to mix-and-match STT/LLM/TTS providers (Deepgram, OpenAI, Anthropic, ElevenLabs, Cartesia) and prefer transparent pass-through pricing over bundled per-minute rates. Skip if you want a no-code drag-and-drop flow builder polished enough for non-engineers, or if you need a single all-inclusive per-minute price without managing separate provider accounts. Skip if your call volume is small enough that the $10/line/month concurrency cost (after 10 included lines) becomes the dominant line item.
How to evaluate Vapi
Use this category when missed calls, slow qualification, or phone support volume affects revenue.
Confirm the exact workflow
Map Vapi to one concrete workflow first, such as build an outbound sales sdr agent that dials leads, qualifies on a script, and books meetings into calendly. Avoid buying before the owner, trigger, output, and success metric are clear.
Check category fit
Test voice quality, latency, interruptions, and escalation behavior.
Compare practical alternatives
Shortlist Vapi against Retell AI, Bland AI, Synthflow so the decision is based on fit, effort, and workflow ownership rather than brand recognition alone.
Validate cost and rollout effort
Build plan is usage-based: $0.05/minute Vapi platform fee, $0.005/message for SMS/chat, 10 concurrent lines included then $10/line/month. STT, LLM, and TTS billed at provider cost ($0 if you bring your own API key). HIPAA compliance is a $2,000/mo add-on; Zero Data Retention is $1,000/mo. Scale plan is annual contract with committed volume, volume-based per-minute pricing, custom concurrency, SOC 2/HIPAA/PCI, SSO/RBAC, and dedicated SLA. Also confirm implementation time, support needs, and whether the medium setup matches your team.
Compare Vapi with alternatives
Use this quick comparison before booking demos or moving data into a new system.
| Primary workflow | Build an outbound sales SDR agent that dials leads, qualifies on a script, and books meetings into Calendly, Replace an after-hours support IVR with a voice agent that can transfer to a human when confidence drops |
|---|---|
| Best-fit team | Voice AI startups and YC-stage teams building branded voice products on top of best-of-breed models, Engineering teams that want STT, LLM, and TTS provider flexibility instead of a black-box bundle |
| Implementation effort | Medium setup and maintenance profile |
| Pricing check | $0.05/min Vapi platform fee plus pass-through model and telephony costs, with per-line concurrency surcharge |
| Closest alternatives | Retell AIBland AISynthflowElevenLabs Conversational AI |
Vapi pricing
| Model | $0.05/min Vapi platform fee plus pass-through model and telephony costs, with per-line concurrency surcharge |
|---|---|
| Snapshot | Build plan is usage-based: $0.05/minute Vapi platform fee, $0.005/message for SMS/chat, 10 concurrent lines included then $10/line/month. STT, LLM, and TTS billed at provider cost ($0 if you bring your own API key). HIPAA compliance is a $2,000/mo add-on; Zero Data Retention is $1,000/mo. Scale plan is annual contract with committed volume, volume-based per-minute pricing, custom concurrency, SOC 2/HIPAA/PCI, SSO/RBAC, and dedicated SLA. |
| Checked |
Common questions about Vapi
What is Vapi?
Vapi is a developer platform for building real-time voice AI agents that handle inbound and outbound phone calls, with sub-500ms latency and bring-your-own-key support for STT, LLM, and TTS providers. Its pricing strategy is transparent: Vapi charges a flat $0.05/minute platform fee and passes through model and telephony costs at provider rates, which means your effective per-minute cost is highly dependent on which models you choose.
What is Vapi used for?
Common use cases: Build an outbound sales SDR agent that dials leads, qualifies on a script, and books meetings into Calendly; Replace an after-hours support IVR with a voice agent that can transfer to a human when confidence drops; Run patient appointment reminder calls with HIPAA mode enabled and pass-through Twilio telephony; Spin up a tenant-isolated voice agent per customer using BYO LLM keys so model costs flow back to them.
How much does Vapi cost?
Build plan is usage-based: $0.05/minute Vapi platform fee, $0.005/message for SMS/chat, 10 concurrent lines included then $10/line/month. STT, LLM, and TTS billed at provider cost ($0 if you bring your own API key). HIPAA compliance is a $2,000/mo add-on; Zero Data Retention is $1,000/mo. Scale plan is annual contract with committed volume, volume-based per-minute pricing, custom concurrency, SOC 2/HIPAA/PCI, SSO/RBAC, and dedicated SLA.
Who is Vapi best for?
Vapi fits Voice AI startups and YC-stage teams building branded voice products on top of best-of-breed models, Engineering teams that want STT, LLM, and TTS provider flexibility instead of a black-box bundle, Agencies deploying voice agents per client with bring-your-own-key cost attribution, High-volume call operations where annual Scale contracts unlock committed-volume per-minute rates. Right for you if you have engineering capacity, want to mix-and-match STT/LLM/TTS providers (Deepgram, OpenAI, Anthropic, ElevenLabs, Cartesia) and prefer transparent pass-through pricing over bundled per-minute rates. Skip if you want a no-code drag-and-drop flow builder polished enough for non-engineers, or if you need a single all-inclusive per-minute price without managing separate provider accounts. Skip if your call volume is small enough that the $10/line/month concurrency cost (after 10 included lines) becomes the dominant line item.
What are alternatives to Vapi?
Common alternatives to Vapi include Retell AI, Bland AI, Synthflow, ElevenLabs Conversational AI, PolyAI, Deepgram.