Vapi

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Pricing model

Usage-based [2]vapi.ai/pricing“Per-minute call hosting: $0.05 / min ... Call concurrency: 10 lines included, additional lines at $10 per line/mo”cloudtalk.io/blog/vapi-ai-pricing/“Vapi operates on a usage-based pricing model rather than traditional plan tiers. Vapi charges $0.05 per minute for their platform.”

Published pricing

✓ Yes [3]vapi.ai/pricing“Per-minute call hosting: $0.05 / min ... SMS/Chat messaging: $0.005 / msg”

Free tier

✓ Yes [4]vapi.ai/blog/free-telephony-with-vapi“a completely free way to use Vapi-managed phone numbers ... Once you've created a free Vapi number, you can make and receive calls at no cost”docs.vapi.ai/phone-calling“Free Vapi phone numbers are only available for US national use ... You can create up to 10 free numbers per account”

Free tier details

Free US phone numbers (up to 10 per account) with free inbound/outbound calls on Vapi-managed US numbers. Separate one-time $10 trial credit (~150-200 minutes) for new users. Build plan otherwise charges $0.05/min with no mandatory monthly base fee.

Self-serve signup

✓ Yes [5]docs.vapi.ai/quickstart/introduction“Build your first voice agent in 5 minutes using our dashboard”

Requires sales call

✗ No

Enterprise plan

✓ Yes [6]docs.vapi.ai/enterprise/plans“Unlimited concurrency and higher rate limits ... Hands-on technical support ... HIPAA BAA and SOC 2 (Type II) certified”

• Built-in telephony
• Outbound calling
• BYO models
• Multilingual

Supported actions

realtime_conversation, inbound_telephony, outbound_telephony, sip_trunking, call_transfer, function_calling, tool_calling, interruption_handling, byo_llm, byo_voice, batch_calling, call_recording, web_widget, knowledge_base, multi_assistant_orchestration, warm_transfer, cold_transfer, dynamic_call_transfer, dtmf, sms_during_call, webhook_events, end_of_call_report, call_analytics, custom_llm_integration, mcp_tool_calling, squad_orchestration [7]docs.vapi.ai/tools/default-tools“transferCall ... endCall ... sms ... dtmf ... apiRequest — make HTTP requests to any external API endpoint during conversations”docs.vapi.ai/calls/call-dynamic-transfers“Dynamic Transfers: Real-time destination selection based on conversation analysis ... Warm Transfers ... Cold Transfers”docs.vapi.ai/advanced/sip/sip-trunk“SIP trunking replaces traditional phone lines with a virtual connection over the internet”

Regions

United States, European Union [8]security.vapi.ai“US and EU deployments”docs.vapi.ai/advanced/sip/sip-trunk“US and EU regions each have dedicated SIP hosts and signaling IP addresses”

Languages

English, Spanish, Italian, French, 110+ languages via Gladia STT, 140+ languages via Azure TTS, 100+ languages via Deepgram, 125+ languages via Google STT

Input types

PSTN phone call, SIP, WebRTC, web widget, audio stream [9]docs.vapi.ai/phone-calling“Vapi provides phone calling capabilities with support for both inbound and outbound calls via the PSTN network”docs.vapi.ai/advanced/sip/sip-trunk“SIP trunking replaces traditional phone lines with a virtual connection over the internet”

Output types

audio stream, call transcript, webhook events, end-of-call report, call recording, structured call summary, SMS [10]docs.vapi.ai/server-url/events“end-of-call-report: Includes recording, transcript, and message artifacts”docs.vapi.ai/tools/default-tools“sms — send SMS messages using a configured Twilio account”

Webhooks

✓ Yes [11]docs.vapi.ai/server-url/events“end-of-call-report: Includes recording, transcript, and message artifacts ... status-update: Call state changes (scheduled, queued, ringing, in-progress, forwarding, ended)”

Sandbox / test mode

✗ No

SDK languages

TypeScript/JavaScript (server), Python (server), Go (server), Java (server), Ruby (server), C# (server), JavaScript/TypeScript (web client), React Native (client), Flutter (client), Swift/iOS (client), Python (client) [12]docs.vapi.ai/sdks“Server SDKs include TypeScript SDK, Python SDK, Java SDK, Ruby SDK, C# SDK, and Go SDK”docs.vapi.ai/resources“Web · Flutter · React Native · iOS · Python · Vanilla”

MCP server

✓ Yes [13]mcp.vapi.ai“Vapi | Model Context Protocol Server”docs.vapi.ai/sdk/mcp-server“Vapi MCP Server”

SOC 2

SOC 2 Type II [14]docs.vapi.ai/faq“SOC 2 Type II certified with regular audits to maintain the certification”docs.vapi.ai/enterprise/plans“HIPAA BAA and SOC 2 (Type II) certified”

HIPAA

✓ Yes [15]docs.vapi.ai/security-and-privacy/hipaa“no call logs, recordings, or transcriptions are stored during or after your calls”vapi.ai/pricing“HIPAA compliance: $2000/mo”

GDPR

✓ Yes [16]docs.vapi.ai/security-and-privacy/GDPR“personal data is transferred outside the European Union (primarily to the United States) using standard contractual clauses”docs.vapi.ai/faq“GDPR compliant for handling EU data”

ISO 27001

– Unknown

PCI DSS

✓ Yes [17]security.vapi.ai“PCI DSS v4.0.1”docs.vapi.ai/security-and-privacy/pci“If no cloud storage or webhook is specified, recordings and transcripts are permanently deleted to avoid retaining sensitive data”

Published SLA

✓ Yes [18]vapi.ai/enterprise“99.9% uptime for enterprise clients”vapi.ai“99.9% reliability with Vapi Dynamic Compute”

Rate limits

10 concurrent call slots by default; additional lines at $10/line/mo self-serve. Enterprise includes custom/unlimited concurrency. 1000+ concurrent sessions is well within Vapi's capacity per FAQ. [19]docs.vapi.ai/calls/call-concurrency“Every Vapi account includes 10 concurrent call slots by default. When all slots are busy, new outbound dials or inbound connections wait until a slot becomes free.”docs.vapi.ai/faq“1000+ concurrent sessions is well within our capacity”

Known restrictions

Default 10 concurrent call slots per account, Free phone numbers limited to US numbers only (up to 10 per account), International numbers require BYO Twilio credentials, HIPAA mode restricts available LLM/TTS/STT providers to compliant subset, HIPAA compliance add-on costs $2,000/month, Zero Data Retention add-on costs $1,000/month, PCI compliance mode limits available models and providers and restricts access to call logs/recordings within Vapi platform, Scale plan requires annual contract and custom pricing via sales [20]vapi.ai/pricing“HIPAA compliance: $2000/mo ... Zero Data Retention: $1000/mo”docs.vapi.ai/calls/call-concurrency“Default concurrency slots: 10 concurrent calls per account”docs.vapi.ai/security-and-privacy/pci“enabling PCI compliance ... restricts you to use only the PCI-compliant endpoints, while limiting access to certain features, such as reviewing call logs, recordings or transcriptions, within the Vapi platform”

• Docs
• llms.txt
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://api.vapi.ai

Versioning

none

Stability

ga

Auth methods

api_key, oauth2, hmac_signature

Error format

vendor-specific

Webhook signing

hmac_sha256

Rate limit

10 / concurrent calls

SDKs

• TypeScript/JavaScript (server) @vapi-ai/server-sdk · repo
• Python (server) vapi · repo
• Go (server) github.com/VapiAI/server-sdk-go · repo
• Java (server) ai.vapi:server-sdk · repo
• Ruby (server) vapi-server-sdk · repo
• C# (server) Vapi.ServerSDK · repo
• JavaScript/TypeScript (web client) @vapi-ai/web · repo
• React Native (client) @vapi-ai/react-native · repo
• Flutter (client) vapi_flutter · repo
• Swift/iOS (client) · repo
• Python (client) · repo

• Auth docs
• Quickstart
• MCP server
• Webhook events

Launched

2024-01-01

Notable customers

Amazon Ring, Kavak, Instawork, New York Life, Intuit, Cherry, UnityAI

• ElevenLabs Conversational AI (ElevenAgents)

  "Deploy human-like Conversational AI in minutes. ElevenLabs delivers low latency interactions in dozens of languages with enterprise-grade security."

  Hybrid · free tier · public pricing · self-serve

• OpenAI Realtime API (gpt-realtime)

  "The Realtime API enables low-latency, bidirectional audio communication for building voice agents and audio applications."

  Usage · public pricing · self-serve

• Telnyx Voice AI Agents

  "Carrier-grade Voice AI from Telnyx. Sub-200ms latency, 80+ languages, A-level STIR/SHAKEN attestation, and one platform that replaces 5 vendors."

  Usage · public pricing · self-serve

• Twilio ConversationRelay

  "Twilio's Conversation Relay empowers you to build powerful AI voice experiences for your customers. Let Twilio handle the heavy lifting of speech recognition, text-to-speech, and voice synthesis."

  Usage · public pricing · self-serve

• Cartesia Line

  "Turn any text agent into a world-class conversational agent, deployed anywhere."

  Hybrid · free tier · public pricing · self-serve

• Pipecat Cloud (Daily)

  "The fastest path to production voice AI" - a managed hosting platform for deploying and scaling Pipecat agents in production with built-in infrastructure.

  Usage · public pricing · self-serve

Vapi alternatives · Vapi vs ElevenLabs Conversational AI (ElevenAgents) · All Realtime Voice Agent APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: vapi.ai
2. ↑Pricing model: vapi.ai · cloudtalk.io
3. ↑Published pricing: vapi.ai
4. ↑Free tier: vapi.ai · docs.vapi.ai
5. ↑Self-serve signup: docs.vapi.ai
6. ↑Enterprise plan: docs.vapi.ai
7. ↑Supported actions: docs.vapi.ai · docs.vapi.ai · docs.vapi.ai
8. ↑Regions: security.vapi.ai · docs.vapi.ai
9. ↑Input types: docs.vapi.ai · docs.vapi.ai
10. ↑Output types: docs.vapi.ai · docs.vapi.ai
11. ↑Webhooks: docs.vapi.ai
12. ↑SDK languages: docs.vapi.ai · docs.vapi.ai
13. ↑MCP server: mcp.vapi.ai · docs.vapi.ai
14. ↑SOC 2: docs.vapi.ai · docs.vapi.ai
15. ↑HIPAA: docs.vapi.ai · vapi.ai
16. ↑GDPR: docs.vapi.ai · docs.vapi.ai
17. ↑PCI DSS: security.vapi.ai · docs.vapi.ai
18. ↑Published SLA: vapi.ai · vapi.ai
19. ↑Rate limits: docs.vapi.ai · docs.vapi.ai
20. ↑Known restrictions: vapi.ai · docs.vapi.ai · docs.vapi.ai

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-21 Capabilities: {} → {"byo_models":true,"multilingual":true,"outbound_calling":true,"telephony_inclu…
2. 2026-06-21 Summary Md: (none) → Vapi is a voice agent platform for building and deploying AI-powered phone agen…
3. 2026-06-21 Score Pricing Transparency: (none) → 100
4. 2026-06-21 Score Setup Speed: (none) → 85
5. 2026-06-21 Score Docs Quality: (none) → 25
6. 2026-06-21 Score Procurement Friction: (none) → 100
7. 2026-06-21 Score Trust Readiness: (none) → 85
8. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
9. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
10. 2026-06-21 Score Agent Friendliness: (none) → 55
11. 2026-06-21 Llms Txt Present: (none) → Yes
12. 2026-06-21 Llms Txt URL: (none) → https://vapi.ai/llms.txt
13. 2026-06-21 Rendering: (none) → static
14. 2026-06-21 Has Structured Data: (none) → No
15. 2026-06-21 Robots Allows Agents: (none) → Yes
16. 2026-06-21 Status Page URL: (none) → https://status.vapi.ai
17. 2026-06-21 Docs URL: (none) → https://docs.vapi.ai/quickstart/introduction
18. 2026-06-21 MCP Server Available: set to Yes
19. 2026-06-21 Pricing Model: set to usage_based
20. 2026-06-21 Has Published Pricing: set to Yes
21. 2026-06-21 Free Tier Available: set to Yes
22. 2026-06-21 Free Tier Details: set to Free US phone numbers (up to 10 per account) with free inbound/outbound calls o…
23. 2026-06-21 Self Serve Signup: set to Yes
24. 2026-06-21 Requires Sales Call: set to No
25. 2026-06-21 Enterprise Plan Available: set to Yes
26. 2026-06-21 SOC 2: set to type_2
27. 2026-06-21 HIPAA: set to Yes
28. 2026-06-21 PCI DSS: set to Yes
29. 2026-06-21 SLA Published: set to Yes
30. 2026-06-21 Data Retention Policy URL: set to https://vapi.ai/terms-of-service
31. 2026-06-21 Documented Rate Limits: set to 10 concurrent call slots by default; additional lines at $10/line/mo self-serve…
32. 2026-06-21 Rate Limit Requests: set to 10
33. 2026-06-21 Rate Limit Window: set to concurrent calls
34. 2026-06-21 Known Restrictions: set to Default 10 concurrent call slots per account, Free phone numbers limited to US …
35. 2026-06-21 Auth Methods: set to api_key, oauth2, hmac_signature
36. 2026-06-21 Auth Docs URL: set to https://docs.vapi.ai/server-url/server-authentication
37. 2026-06-21 API Style: set to rest
38. 2026-06-21 Base URL: set to https://api.vapi.ai
39. 2026-06-21 Versioning Scheme: set to none
40. 2026-06-21 Stability: set to ga
41. 2026-06-21 MCP URL: set to https://docs.vapi.ai/_mcp/server
42. 2026-06-21 Quickstart URL: set to https://docs.vapi.ai/quickstart/introduction
43. 2026-06-21 Error Format: set to vendor-specific
44. 2026-06-21 Webhook Signing: set to hmac_sha256
45. 2026-06-21 Webhook Events URL: set to https://docs.vapi.ai/server-url/events
46. 2026-06-21 Requires Verification: set to No
47. 2026-06-21 Starting Price Usd: set to 0.05
48. 2026-06-21 Price Basis: set to minute
49. 2026-06-21 Launched At: set to 2024-01-01
50. 2026-06-21 Notable Customers: set to Amazon Ring, Kavak, Instawork, New York Life, Intuit, Cherry, UnityAI

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/vapi \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/vapi/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →