# Vapi — Developer platform for building, testing and deploying voice AI agents that make and receive phone calls.

> Source: The Agents Index — https://theagentsindex.com/vapi (structured, researched, re-verified)
> Facts last verified: 2026-09-03

Vapi is a developer platform for voice AI agents that make and receive phone calls, orchestrating a speech-to-text, LLM and text-to-speech pipeline on its own infrastructure. Every component is swappable, and Vapi's proprietary turn-taking, interruption and endpointing models run only on its side.

| Fact | Value |
| --- | --- |
| Website | https://vapi.ai |
| Price | from $0.05/minute pay-as-you-go |
| Free trial | Partly |

$5 in free credits on signup with no credit card; there is no standing free plan, minimum credit top-up is $10, and 10 concurrent call lines are included on the Build plan.

## What it does

**Done-for-you service** · Partly — You build and run the agent yourself; the Scale contract adds an embedded Vapi engineer for the go-live, not a done-for-you build.

> A dedicated engineer embedded in your team to get you live in a week.
> — https://vapi.ai/ · Built for Enterprises section, Dedicated Deployment Support card

## How much it does unattended

**Runs autonomously** · Yes — Agents take whole calls end to end and escalate to a human only when the configured path says so.

> Automate inbound support calls with agents that can access your knowledge base and escalate to humans when needed.
> — https://docs.vapi.ai/quickstart/introduction · Popular use cases, Customer Support card

**Multi-agent** · Yes — Squads route one conversation across several specialised assistants with context-preserving handoffs.

> Squads orchestrate multiple assistants with context-preserving transfers.
> — https://docs.vapi.ai/quickstart/introduction · Two ways to build voice agents, Squads card

**Agent permissions** · Partly — Tools fire mid-call without human approval; a per-tool rejection plan is the mechanism that withholds an action.

> A rejection plan lets you prevent a tool from executing when certain conditions are met.
> — https://docs.vapi.ai/tools/tool-rejection-plan · Overview, first sentence

## Which models it runs on

**Claude** · Yes — Claude is selectable as the assistant's LLM, on Vapi's integration or your own Anthropic account.

> Anthropic builds the Claude family of large language models. On Vapi, you select a Claude model as the LLM for a voice agent.
> — https://docs.vapi.ai/providers/model/anthropic · What is Anthropic section

**GPT** · Yes — OpenAI GPT models are selectable as the assistant's LLM.

> Set model.provider to openai and model.model to a GPT model.
> — https://docs.vapi.ai/providers/model/openai · Language model section

**Open models** · Yes — Open-weight models reach the pipeline through Groq, Together AI, Mistral, DeepSeek and OpenRouter, or a self-hosted server.

> Bring your own API keys for transcription, LLM, or TTS — or plug in your own self-hosted models.
> — https://vapi.ai/platform · Features section, Bring your own models card

**Model choice** · Yes — You choose transcriber, LLM and voice independently and can swap any of them.

> Bring your own model, or choose from our managed list of 200+ models and integrations.
> — https://vapi.ai/platform · Developer-first section, Custom model support card

## Where you use it

**In your editor** · Partly — No agent runtime in the editor; `vapi mcp setup` teaches Cursor, Windsurf and VSCode the Vapi API so you can build from the IDE.

> Your IDE's AI assistant (Cursor, Windsurf, VSCode) gains complete, accurate knowledge of Vapi's APIs and best practices.
> — https://docs.vapi.ai/cli · Key features, MCP integration section

**On the command line** · Yes — The Vapi CLI covers assistants, numbers, calls, campaigns and logs from the terminal.

> The Vapi CLI is the official command-line interface that brings world-class developer experience to your terminal and IDE.
> — https://docs.vapi.ai/cli · Overview, first paragraph

**In your pipeline** · Partly — Evals run as pipeline quality gates via API and CLI; there is no pull-request surface because there is no code to review.

> CI/CD integration - Automate quality gates in your deployment pipeline
> — https://docs.vapi.ai/observability/evals-quickstart · When are Evals useful? list, sixth bullet

**In a browser** · Yes — A hosted dashboard builds and observes agents, and calls embed in your own web app via the Web SDK and widget.

> Web integration: Embed voice calls directly in your applications
> — https://docs.vapi.ai/quickstart/introduction · Key capabilities list, second bullet

## Whose machine it runs on

**Self-hosted** · Partly — Self-serve is hosted only; on-premise is offered to large enterprises, and the orchestration layer otherwise never leaves Vapi.

> Yes, we support on-premise deployments for large Enterprises.
> — https://docs.vapi.ai/faq · Frequently Asked Questions, on-premise deployments entry

**Open source** · Partly — The CLI and SDKs are MIT-licensed on Vapi's GitHub; the platform and its orchestration models are closed and hosted.

> MIT License - see LICENSE file for details.
> — https://github.com/VapiAI/cli · README.md, License section

## What it costs to run

**How it meters** · Yes — Per call minute for Vapi hosting, plus model provider cost passed through at cost, plus $10 per concurrent line per month.

> $0.05 / min
> — https://vapi.ai/pricing · Compare Features table, Vapi Hosting Cost > Calls row, Build column

**Free tier** · Yes — Self-serve signup with a $5 credit grant and no card; it is a grant against usage, not a standing free tier.

> Yes, every new account gets $5 in free credits to start building without the need for credit card.
> — https://vapi.ai/pricing · Frequently asked questions, 'Can I try Vapi for free?'

**API access** · Yes — REST API covers every capability; server and client SDKs wrap it.

> Every capability is accessible via REST API. Your team owns the integration end to end.
> — https://vapi.ai/platform · Customize section, API-First Architecture card

**MCP server** · Yes — A hosted MCP server exposes assistants, calls and numbers to another agent, and assistants can also call external MCP servers.

> The Vapi MCP Server exposes Vapi APIs as tools via the Model Context Protocol (MCP), so you can manage assistants, phone numbers, and calls from any MCP-compatible AI assistant
> — https://docs.vapi.ai/sdk/mcp-server · Overview, first paragraph

**Bring your own key** · Yes — Provider keys for transcriber, LLM, voice and storage; with your key the model cost drops out of the Vapi bill entirely.

> At cost ($0 if you bring your own API key)
> — https://vapi.ai/pricing · Compare Features table, Model Provider Cost > Calls row, Build column

## Buying it for a team

**A company can buy it** · Yes — Billing, credits, add-ons and concurrency all belong to an organization, purchased by a member with the Admin role.

> Purchase call concurrency from Billing & Add-Ons to increase the number of simultaneous calls available to your Vapi organization.
> — https://docs.vapi.ai/billing/purchase-call-concurrency · Page summary line

**Seat model** · No — Nothing is priced per seat: the plan table meters call minutes and concurrent lines only, and members are invited with RBAC roles.

> 10 included + $10 / line / mo
> — https://vapi.ai/pricing · Compare Features table, Usage and Scale > Call Concurrency row, Build column

**Pooled budget** · Yes — One organization credit balance and one concurrency pool; every inbound and outbound call draws on the same capacity.

> All inbound and outbound calls share the organization's capacity.
> — https://docs.vapi.ai/billing/purchase-call-concurrency · How call lines affect concurrency section

**Admin controls** · Yes — Per-tool rejection conditions withhold an action, API keys are scoped to specific origins and assistants, and prompt guardrails override other instructions.

> Every API key belongs to one Vapi organization. Choose the key type based on where your application runs, then limit the key to the origins and assistants that need access.
> — https://docs.vapi.ai/security-and-privacy/api-keys · How it works section

**Audit log** · Partly — The dashboard keeps org-wide API, call and webhook logs and assistant version history; no member-action audit trail is documented.

> Monitor all API requests and responses
> — https://docs.vapi.ai/debugging · Dashboard debugging resources, API Logs section, first bullet

**Single sign-on** · Partly — SAML 2.0 or OIDC with any IdP, but enterprise-only and without SCIM provisioning; the Build column shows a dash.

> Vapi works with any IdP that supports SAML 2.0 or OpenID Connect (OIDC), including Google Workspace, Microsoft Entra ID (formerly Azure AD), and Okta.
> — https://docs.vapi.ai/security-and-privacy/sso · Overview, second paragraph

## What happens to your code

**Opt out of training** · Partly — The privacy policy reserves call content for model training and names no toggle; the $1,000/month ZDR add-on is the only documented way to stop it being kept at all.

> Call recordings, transcripts and logs may be retained to help train and improve the AI models, in accordance with applicable laws.
> — https://vapi.ai/privacy · Section 2. Calls

**Data residency** · Partly — US is the default region; the EU region is frozen to existing accounts and new EU residency is enterprise-only, so regional control comes from your own buckets and models.

> Vapi's EU support and self-serve growth are frozen until 2027. Existing EU customers can continue using their accounts, but Vapi is not offering new add-ons
> — https://docs.vapi.ai/security-and-privacy/data-flow · Recommendations by Use Case, Data residency compliance section

**Getting out** · Yes — Credits are bought upfront and spent over any time frame rather than lapsing at month end.

> You can load credits upfront and use them over any time frame that suits your usage patterns - so you're not penalized for underuse in any given month.
> — https://vapi.ai/pricing · Frequently asked questions, 'Can I get fixed monthly pricing instead of pay-as-you-go?'

**Certifications** · Partly — SOC 2 Type II and a HIPAA BAA sit in the Scale contract, and the plan table shows SOC2 only in that column; HIPAA mode is a $2,000/month add-on on either plan.

> HIPAA BAA and SOC 2 (Type II) certified
> — https://docs.vapi.ai/enterprise/plans · Enterprise Plans can include list, fifth bullet

## Provenance

Every fact above comes from the vendor. Nothing here is independently corroborated yet.

## Coverage elsewhere

Pages about this product that the vendor does not control. The label states how independent each one is.

| Source | Kind | Read |
| --- | --- | --- |
| lindy.ai | A competitor's comparison | 2026-08-23 |
| techcrunch.com | Independent source | 2026-08-23 |

## What changed

- 2026-09-03 — Capabilities · Commercial terms · Free tier
- 2026-08-31 — Capabilities · Commercial terms · Free tier · Price
- 2026-08-22 — Alternatives · Crunchbase link · Documentation link · LinkedIn link · Repository · Summary
- 2026-08-19 — Summary

## Correcting this record

Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Vapi, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth.

Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.