Retell AI vs Vapi
A side-by-side comparison of Retell AI and Vapi on what each one charges, what it meters, and which plan every capability actually sits on.
The short answer
5 of the 20 capabilities tracked on both differ, mostly in Enterprise.
| Measure | Retell AI | Vapi |
|---|---|---|
| Starts at | Sales-gated | Sales-gated |
| AI billed at | $0.00 per AI interaction | $0.01 per AI interaction |
| Included, where the other says no | 0 capabilities | 1 capability |
Capability by capability
5 of the 20 capabilities tracked on both products differ.
Channels
| Capability | Retell AI | Vapi |
|---|---|---|
| Live chat | IncludedPay-as-you-go. Chat agents are billed per AI message, from $0.001 to $0.052 depending on model. | IncludedBuild, at $0.005 a message. A Chat API with streaming and non-streaming modes, an OpenAI-compatible endpoint, session management, and a drop-in web widget that runs in chat or voice mode from one script tag. |
| Voice | IncludedPay-as-you-go. Voice is the product, billed per connected minute. | IncludedBuild. Voice is the product, billed at $0.05 a minute of connected call time on top of provider cost. |
| SMS | Paid add-on$0.01 per message on both call and chat agents, plus a $20.00 monthly Retell SMS subscription. No charge on custom telephony. | IncludedBuild, billed on the same $0.005 a message meter as chat. Requires a 10DLC-approved Twilio number, and inbound SMS is documented as US only. |
AI resolution
| Capability | Retell AI | Vapi |
|---|---|---|
| Resolution over knowledge base | Paid add-onKnowledge Base is metered twice: $0.005 a minute when an agent uses one, and $8.00 a month per knowledge base above the first ten. | IncludedA query tool retrieves from knowledge bases built in Vapi, billed as a knowledge-base line in the call cost array. A custom knowledge base server is the documented alternative, and keeps the corpus out of Vapi entirely. |
| Action-taking (API calls) | IncludedTool calls are first-class and readable after the fact through transcript_with_tool_calls. On a Custom LLM agent your own tool calls only appear in the transcript if you report them yourself. | IncludedTools are first-class and versioned: an API Request tool with configurable retries, custom function tools, client-side tools in the web SDK, argument encryption, and a tool rejection plan. Squad handoffs carry a contextEngineeringPlan controlling how much conversation and how many tool results move to the next assistant. |
| Handoff to human | IncludedTransfer stops the AI voice agent fee and leaves only telephony running. Agent transfer cannot target a Custom LLM agent. | IncludedBlind transfer, warm transfer, assistant-based warm transfer, dynamic destinations and on-hold specialist transfer are each documented separately. Nothing published says the $0.05 hosting meter stops when a call reaches a human. |
| Guardrails & citations | Paid add-onSafety Guardrails at $0.005 a minute, listed as a feature of both tiers but metered. Citation behaviour is not published, so only half of this attribute is evidenced. | Not published |
| Multilingual AI | Not publishedNo language list or count appears on the pricing page, the compliance docs, the integrations page or the custom-LLM docs. | Via middlewareDelivered by whichever third-party transcriber you select rather than by Vapi, which ships no speech recognition of its own and publishes no language count. The docs compare providers instead: Deepgram 100+ languages with auto-detection, Google STT 125+, Gladia 110+, AssemblyAI 18, while Azure, Whisper, Speechmatics and Talkscriber carry many languages but cannot detect them. So whether an agent can switch language mid-call is a consequence of a configuration choice, and the documented way to tell the agent it is multilingual is to list the languages in your own system prompt. |
AI voice
| Capability | Retell AI | Vapi |
|---|---|---|
| Voice agent | IncludedTelephony arrives through Twilio elastic SIP trunking or SIP connectors for Five9, Telnyx and Vonage, or through Retell-issued numbers at $2.00 a month. | IncludedTransport is modular: SIP, WebSocket, WebRTC via LiveKit or Daily, or PSTN through an imported Twilio, Telnyx, Plivo, Vonage, DIDWW, Zadarma, didlogic or Amazon Chime number. Up to five free Vapi US numbers per account, US area codes only. |
| Real-time transcription | IncludedThe API returns transcript_object with word-level timings, plus a scrubbed variant. The speech-to-text engine runs for the whole call, which is also why silence is billed. | IncludedStreaming recognition from a choice of eleven transcriber providers, or your own over a WebSocket. Both the caller and the assistant are transcribed, which is why a minute of call is two channels of audio on the provider bill. |
| Call summarization | Not published | IncludedCall analysis produces a summary and schema-defined structured outputs after the call, attached to the call record and readable through the API. Under HIPAA mode structured outputs are not stored unless each one is explicitly opted in. |
QA & workforce
| Capability | Retell AI | Vapi |
|---|---|---|
| Automated QA coverage | Paid add-onAI Quality Assurance at $0.10 a minute, first 100 minutes free. No export path for its output is documented. | IncludedScorecards grade every call automatically by awarding points when structured outputs meet conditions you define, landing in call.artifact.scorecards within seconds of call end. No per-call charge is published for grading, unlike Retell's $0.10 a minute. API only for now, by the vendor's own admission. Evals and AI-driven simulations sit alongside for pre-production testing. |
Reporting
| Capability | Retell AI | Vapi |
|---|---|---|
| Raw data export | API onlyCalls, transcripts and recordings come out through the API. There is no export UI, and bulk retrieval is unverified. | API onlyEverything comes out through the API or a mirrored bucket; there is no export UI. Recordings and logs are served as 302 redirects to short-lived signed URLs against a private bucket, so a cached URL stops working. |
Enterprise
| Capability | Retell AI | Vapi |
|---|---|---|
| SAML SSO | IncludedEnterprise only. Absent from pay-as-you-go. | IncludedEnterprise only, marked "-" against Build on the pricing page. SAML 2.0 or OIDC against any IdP, with Google Workspace, Microsoft Entra ID and Okta named. |
| SCIM provisioning | Not published | NoStated outright in the SSO documentation: "Vapi does not support SCIM provisioning." Members sign themselves up and an administrator invites them, so removing a leaver is a manual step even on an SSO contract. |
| Role-based access control | IncludedEnterprise only. Absent from pay-as-you-go, which has no user or role model priced at all. | IncludedThe pricing page prints RBAC as a Scale row with "-" against Build, while the SSO documentation describes the three roles as ordinary organization behaviour. Which of the two governs a Build account is not resolved by anything published. |
| HIPAA / BAA | IncludedAvailable on pay-as-you-go, not enterprise-gated. Self-serve signing at click-agreements.retellai.com at no additional cost, countersigned inside a business day. | Paid add-on$2000/mo add-on, priced identically on Build and Scale, or included by negotiation on an Enterprise subscription. A signed BAA is required first, started by emailing security@vapi.ai. Organization-wide with no per-assistant exception, not settable through the API, and mutually exclusive with Zero Data Retention. |
| SOC 2 | IncludedNo plan gate stated. Type 1 and Type 2. | IncludedThe trust center lists SOC 2 with reports behind an access request, while the pricing page prints SOC2 as a Scale-only row. The certification is account-wide; the report and the contractual commitment are what the enterprise tier buys. |
| GDPR | IncludedNo plan gate stated. A DPA with Standard Contractual Clauses covers EU and UK data subjects, because there is no EU service operation to keep the data in. | IncludedListed on the trust center alongside CCPA. The compliance page names its legal bases, enumerates data subject rights including portability, publishes its third-party processors, and covers transfers to the United States under standard contractual clauses. A full subprocessor register is public, with each entry showing purpose and processing location, which is more than most of this census publishes. |
| Data residency | NoNo customer-selectable region exists. The vendor states it does not currently operate services within the European Union, and recording URLs resolve to AWS us-west-2. | IncludedAn isolated EU region exists (dashboard.eu.vapi.ai, api.eu.vapi.ai, sip.eu.vapi.ai) with its own outbound IP block, and an organization belongs to exactly one region. It is closed to new self-serve signups: EU support and self-serve growth are frozen until 2027, feature parity with the US is not guaranteed, and EU residency is reachable only through sales. |
| Data retention policy | IncludedCustom data retention is listed on both tiers. Configurable per agent from 1 day to 2 years, covering transcripts, recordings and logs. Three privacy modes are documented: store all data, exclude PII, or retain only basic attributes. | IncludedFixed rather than configurable on Build: 14 days of call history, 30 days of chat history. Custom on Scale. Per-assistant artifactPlan flags switch recording, logging and transcription off individually, and PCI mode deletes recordings and transcripts permanently when no bucket or webhook is configured. |
| Right-to-erasure tooling | IncludedAccount deletion plus a support request for full erasure including third-party identifier removal. | IncludedBy request to support@vapi.ai under GDPR and CCPA. The privacy policy states that retention depends on the customer's configuration and that data is deleted on request, while also reserving the right to retain recordings, transcripts and logs to train and improve the AI models. |
Developer
| Capability | Retell AI | Vapi |
|---|---|---|
| REST API | IncludedNo plan gate. A dashboard API key works on pay-as-you-go. | IncludedNo plan gate. A private key from the dashboard works on Build. |
| Webhooks | Not published | IncludedServer URLs with authenticated server events, an end-of-call-report event, campaign pre-dial webhooks, and local development tooling in the CLI. |
| SDKs | IncludedOfficial Node (retell-sdk) and Python (retell) SDKs. Custom LLM lets a customer run the model on their own WebSocket server, with reference implementations for OpenAI, Azure OpenAI, OpenRouter and Claude. | IncludedServer SDKs for TypeScript and Python, real-time SDKs for web, iOS, Flutter, React Native and a vanilla script tag, an official CLI, and a docs MCP server. Custom transcriber, custom LLM and custom TTS servers are each documented, so every pipeline stage except the proprietary orchestration layer can run on your own infrastructure. |
Both entries last checked Sep 9, 2026.
What Retell AI costs
- Billing unit
Pure consumption with monthly capacity line items and no seat dimension - Free tier
No - AI pricing
Not published - Vendor calls it
GPT 5 nano - Human handoff
Still billed - Reopened chat
Not published - AI billing window
Not published - Data export
Self-serve - Automation export
Not published
4 of 9 not published by Retell AI, checked
What Vapi costs
- Billing unit
Pure consumption against a prepaid credit balance - Free tier
No - AI pricing
$0.05 per minute - Vendor calls it
Vapi Hosting - Human handoff
Still billed - Reopened chat
Not published - AI billing window
Not published - Data export
Self-serve - Automation export
Full
2 of 9 not published by Vapi, checked