Agentic Index
Retell AI vs Vapi (2026)
Retell AI and Vapi are the closest head to head in developer voice agents, both unbundled and pay as you go: Retell charges no platform fee with a voice engine at seven to eight cents a minute plus LLM and telephony billed separately (all in commonly thirteen to thirty one cents, enterprise volume near five cents), while Vapi charges a five cent per minute platform fee with every component at provider passthrough (about 8 to 13 cents a minute all in at its default providers, by Vapi's own calculator), plus a paid HIPAA add on, with zero data retention included in any success package. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
The decision usually comes down to API ergonomics, latency in your region, and which compliance packaging fits.
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Retell AI and Vapi are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 955 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Retell AI if
- Twenty free concurrent calls and ten dollars in credits make evaluation friction free.
- Bundled voice engine pricing with separate LLM choice balances simplicity and control.
- Enterprise rates near five cents a minute with HIPAA and BAA fit your scale plans.
Choose Vapi if
- Full provider passthrough on every layer gives maximum stack transparency.
- You want the largest ecosystem of integrations and community examples.
- Committed volume enterprise contracts match your procurement style.
| Feature | R Retell AI |
V Vapi |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
Retell AIIntegrations & Tool Calling An Apps framework holds credentials for each external system, with agent functions across CRM (Salesforce, HubSpot, Dynamics 365, Zoho, GoHighLevel), helpdesk (Zendesk), scheduling (Calendly, Cal.com) and file storage (Google Drive, OneDrive), plus custom functions calling any HTTP API mid-call, a code tool running JavaScript, and MCP tools and nodes reaching remote MCP servers during a live conversation. Contact data also syncs both ways with the CRM. Sourcedocs.retellai.com/integrations/overviewread 2026-09-05 |
||
|
VapiIntegrations & Tool Calling Function tools call the customer's server logic, and API Request tools call any HTTPS API directly with credentials held by reference. MCP tools connect an assistant to external MCP servers at runtime. Built in tools transfer calls, end calls, send SMS and press DTMF keys, and prebuilt integrations include Google Calendar event creation, Make and n8n. Deepgram, OpenAI and other providers are model layers, not integrations. SourceVapi, docs.vapi.ai (Function tools, Integrations, Built-in tools)read 2026-09-27 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
Retell AIWorkflow Orchestration Conversation flow agents are node-and-edge graphs with conversation, subagent, function, code, logic split, extract-variable, SMS, transfer and global nodes, transitions gated by either LLM-evaluated prompt conditions or deterministic equations, reusable subflows shared across flows, and Flex Mode compiling the graph into a runtime prompt for varied caller behavior. Multi-prompt state agents and agent-to-agent transfer cover the same ground for prompt-built agents, with versions and environment tags controlling what is live. Sourcedocs.retellai.com/build/conversation-flow/overviewread 2026-09-05 |
||
|
VapiWorkflow Orchestration Squads split a call across specialized assistants that hand off to each other through handoff tools with declared destinations, resolved at runtime. Context passing, variable extraction and rejection rules are all configurable, and the squad examples route callers by verification and inquiry type. Vapi's older Workflows builder has been retired and its flows moved to Squads. SourceVapi, docs.vapi.ai (Introduction to Squads, Handoff tool, Workflows migration guide)read 2026-09-27 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
Retell AITriggers & Channel Coverage Agents take inbound and outbound calls on Retell-managed numbers or imported ones over elastic SIP trunking, with setup for Twilio, Telnyx, Vonage, Avaya Aura, Genesys Cloud, Five9 and Amazon Connect. They also run browser web calls, a website widget in chat, voice and callback modes, two-way SMS and MMS, and scheduled batch call campaigns, and an inbound call and SMS webhook picks the agent and passes per-call context at ring time. Sourcedocs.retellai.com/deploy/custom-telephonyread 2026-09-05 |
||
|
VapiTriggers & Channel Coverage Outbound campaigns carry a schedulePlan with an earliest and latest dispatch time, so Vapi starts dialing a contact list on its own schedule, with pre dial webhooks. Assistant hooks run actions on call events. Agents also answer on Vapi, Twilio, Telnyx and SIP numbers, in web calls and over SMS chat. SourceVapi, docs.vapi.ai (Campaign scheduling and lifecycle, Assistant hooks, SIP introduction, SMS chat)read 2026-09-27 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
Retell AIKnowledge Grounding & RAG The platform builds and maintains knowledge bases from sources attached as URLs, documents across roughly twenty file formats, or custom text, chunking, embedding and storing them in a vector database at creation time, with retrieval tuned by query-rewrite instructions that condense recent dialogue into a standalone search query. Google Drive and OneDrive sources re-sync on a 24-hour refresh cycle, and knowledge bases are managed independently of any one agent through their own API. Sourcedocs.retellai.com/build/knowledge-baseread 2026-09-05 |
||
|
VapiKnowledge Grounding & RAG Knowledge bases are the customer's uploaded files, such as txt, pdf, docx, csv, md and more, added through the dashboard or the file API, kept in Vapi and attached to assistants. During a call the query tool searches them by file ID, with Google Gemini models doing the retrieval, and new knowledge is added by uploading a file instead of retraining. A custom knowledge base can swap in the customer's own retrieval server. SourceVapi, docs.vapi.ai (Knowledge bases, Query tool)read 2026-09-27 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
Retell AIMemory & State Persistence Contact records keyed by phone number carry custom fields populated by post-call extraction mappings, so the agent recalls preferences, past issues and commitments across every later conversation, with a merged timeline of that contact's calls and chats and a backfill job that re-applies mappings to historical calls. Scope is per contact and the record is separately deletable. It is implemented as contact field mappings, so retention follows the contact record. Sourcedocs.retellai.com/integrations/build-contact-memoryread 2026-09-05 |
||
|
VapiMemory & State Persistence For chat and SMS, a sessionId groups chats under one persisted conversation that expires 24 hours after creation by default (expirationSeconds). Sessions can be read in session logs and deleted through the API, and within a call, squads carry context across handoffs. Nothing the agent learns about a caller is kept beyond the session. SourceVapi, docs.vapi.ai (Session management, Session logs)read 2026-09-27 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
Retell AIHuman Oversight & Guardrails Guardrails detect prohibited topics in both agent responses and user input and replace flagged content with a safe placeholder before it is spoken, and live monitoring lets a person follow the transcript in real time, listen in silently, take over from the agent mid-call or end the call, with an Update Live Call endpoint to inject context or trigger a response on a running session. Sourcedocs.retellai.com/features/live-monitoringread 2026-09-05 |
||
|
VapiHuman Oversight & Guardrails A tool rejection plan attaches conditions to any tool and blocks the call when the recent conversation state matches them, and handoff rejection rules block unwanted transfers between assistants. Transfer tools hand a caller to a person by blind or warm transfer. There is no approval step that holds an action until a person signs off, so escalation hands over the whole conversation. SourceVapi, docs.vapi.ai (Tool rejection plan, Transfer Call tool)read 2026-09-27 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
Retell AISecurity, Identity & Governance Retell is SOC 2 Type 1 and Type 2 certified and HIPAA and GDPR compliant, with a BAA, a DPA and a GDPR erasure process. Customer controls include role-based access control with Admin, Developer, Analyst and Viewer roles, API keys scoped read or edit per area, a webhook signing key with signature verification and IP allowlisting, expiring signed URLs for recordings and logs, per-agent data storage settings and a per-agent retention policy. Sourcedocs.retellai.com/general/complianceread 2026-09-05 |
||
|
VapiSecurity, Identity & Governance Vapi supports SSO through any SAML 2.0 or OIDC identity provider on the Enterprise and Premier plans, and RBAC with Admin, Editor and Viewer roles assigned per member. SCIM is not supported. Vapi's SafeBase trust center announces a completed SOC 2 Type II examination, with the report under NDA, and a public SOC 3, and lists HIPAA, PCI DSS v4.0.1, GDPR and CCPA. HIPAA mode and zero data retention are organization settings. SourceVapi, docs.vapi.ai (Single Sign-On) and security.vapi.airead 2026-09-27 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
Retell AIObservability & Auditability A monitor-call WebSocket streams transcript, tool call and node events from a live session, so the path the agent took through the flow is reconstructable turn by turn, backed by session history with transcripts and CSV export, per-call P50, P90 and P99 latency, disconnection reason codes, call_started, call_ended and call_analyzed webhooks, and AI QA scoring calls on hallucination rate, knowledge base accuracy, tool usage, latency and sentiment against customer-defined cohorts. Sourcedocs.retellai.com/api-references/monitor-call-websocketread 2026-09-05 |
||
|
VapiObservability & Auditability Call logs hold the transcript, messages, analysis, costs, latency, recordings and downloadable pipeline logs for each call, with chat, session, webhook and API request logs beside them. Monitors evaluate call data against thresholds and open issues. Raw data is kept for 14 to 180 days depending on the package. SourceVapi, docs.vapi.ai (Call logs, Logs overview, Monitoring quickstart) and vapi.ai/pricingread 2026-09-27 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
Retell AIDeployment & Data Residency Data storage settings and a retention policy set per agent, plus expiring signed URLs, control what is stored and for how long, but not where data lives. Retell offers no region selection, VPC, single tenant, self hosted or on premises option, and its reliability page describes shared enterprise infrastructure without naming a region. Sourcedocs.retellai.com/accounts/data-retentionread 2026-09-05 |
||
|
VapiDeployment & Data Residency Each organization belongs to the United States or the European Union region, with its own dashboard, API and SIP hosts, such as api.eu.vapi.ai and sip.eu.vapi.ai in the EU. Every resource stays in its region, and each region is an isolated environment. The service is hosted only, with no self hosted or customer tenant option. SourceVapi, docs.vapi.ai (EU region and data residency)read 2026-09-27 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
Retell AIPrebuilt Agents, Templates & Packs The quick start has the customer pick a template as the first build step, Agent Handbook ships toggleable preset prompt packs for personality, accuracy and safety, and reusable subflows package parts of a conversation flow as shared components adopted across agents. The template catalog sits inside the dashboard, and Retell does not publish how broad it is. Sourcedocs.retellai.com/get-started/quick-startread 2026-09-05 |
||
|
VapiPrebuilt Agents, Templates & Packs Cloneable example builds cover appointment scheduling, medical triage and scheduling, ecommerce order management, property management routing, lead qualification and multilingual support. Each does a different job, but the customer builds each one step by step instead of adopting a packaged agent. Model Intelligence presets are settings. SourceVapi, docs.vapi.ai (Guides)read 2026-09-27 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
Retell AIModel Flexibility & Routing The customer picks the language model in agent settings and tunes temperature, fast tier, structured output, retries and timeouts, choosing across providers including OpenAI, Anthropic and Google, or runs their own model entirely through the custom LLM WebSocket protocol while Retell handles telephony, transcription and turn-taking. Speech recognition and text-to-speech providers are separately selectable. Sourcedocs.retellai.com/build/llm-optionsread 2026-09-05 |
||
|
VapiModel Flexibility & Routing Each assistant's transcriber, model and voice can be swapped for any supported provider. Customers can use their own provider keys, Azure OpenAI and Bedrock credentials, or their own server acting as the LLM. Transcriber and voice fallback plans switch providers automatically on failure. SourceVapi, docs.vapi.ai (Core Models, Provider Keys, Custom LLM, fallback configuration)read 2026-09-27 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
Retell AIAPIs, SDKs & MCP Extensibility Retell publishes a REST API at api.retellai.com with an OpenAPI specification and a Postman collection, covering calls, chats, agents, response engines, knowledge bases, contacts, apps, tests and phone numbers. Developers also get official TypeScript and Python SDKs, a browser Web SDK, a command line interface, a hosted MCP server at mcp.retellai.com for Cursor, Claude Desktop and Claude Code, signed webhooks, and an LLM WebSocket protocol for bringing your own model. A published deprecation feed with dated breaking-change notices sits alongside it. Sourcedocs.retellai.com/api-references/overviewread 2026-09-05 |
||
|
VapiAPIs, SDKs & MCP Extensibility The API covers assistants, squads, calls, chats, campaigns, sessions and phone numbers, with server SDKs, a Web SDK and a CLI beside it. The Vapi MCP Server at mcp.vapi.ai, authenticated by bearer token, manages assistants, phone numbers and calls from any MCP client. SourceVapi, docs.vapi.ai (API reference, Vapi MCP Server)read 2026-09-27 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
Retell AITesting, Debugging & Optimization Retell ships five testing surfaces with readable results. An LLM Playground inspects tool calls and transitions and replays any turn, LLM simulation testing has an AI-simulated user run a scenario while success criteria grade each run, and batch tests over many cases report pass rate and per-case results in a testing history. Web and phone call testing and production A/B testing, which splits live traffic between agent versions, complete the set. Test case definitions, batch tests and test runs each have their own API. Sourcedocs.retellai.com/test/test-overviewread 2026-09-05 |
||
|
VapiTesting, Debugging & Optimization Evals test assistants and squads with mock conversations, using exact, regex or AI judged checks and tool call checks, and return pass or fail. Simulations run full conversations against AI testers with success criteria and tool mocks, and the testing guides set a release and regression cadence. SourceVapi, docs.vapi.ai (Evals quickstart, Simulations overview, Run and maintain tests)read 2026-09-27 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
Retell AIBrowser & Computer Use Agents cannot control a browser, a desktop session or a remote computer. The Press Digit tool and press digit node let the agent infer and press keypad digits to walk a third party's DTMF input IVR menu on an outbound call, and voicemail handling detects and responds to another system's automated flow. Sourcedocs.retellai.com/build/single-multi-prompt/press-digitread 2026-09-05 |
||
|
VapiBrowser & Computer Use Browser, desktop and computer control are not described. IVR navigation presses DTMF keys to walk a phone menu on a telephone keypad, not a screen. Web SDK client side tools trigger side effects in the customer's own web app, which is the product running in a browser. SourceVapi, docs.vapi.ai (llms.txt, IVR Navigation, Client-side tools)read 2026-09-27 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | R Retell AI |
V Vapi |
|---|---|---|
|
Entry price Lowest public entry point |
Pay as you go from $0 with $10 in free credits, then $0.07 to $0.31 a minute for voice agents. Voice infrastructure is $0.055 a minute, with the voice, LLM and telephony billed separately on top. Enterprise is custom. | $0.05 a minute hosting fee plus provider costs, usage based. Success packages from $29 a month. |
|
Pricing confidence How public the numbers are |
Public, partial | Public, exact |
|
Billing Primary billing axis |
Usage, billed per connected minute across separately priced components for voice infrastructure, the voice, the LLM and telephony. | Usage, billed per call minute and prepaid. |
|
Variable cost Workload / overage exposure |
High variable cost | High variable cost |
|
Free tier / trial Try before you buy |
Free tierTrial
|
Free tierTrial
|
|
Buying motion Self-serve vs sales call |
Mixed | Mixed |
More comparisons with Retell AI or Vapi
Other matchups in voice agents
Not the pairing you were after? These compare a different set of voice agents on the same 14 capabilities.