Back to vendors
R

Retell AI

Also known as: Retell, Retell AI

Visit site
Entry pricePay 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.Full pricing detail

Voice and chat agent platform for phone workflows, pairing a customer-chosen or self-hosted LLM with node-based conversation flows, telephony over SIP or imported numbers, and a testing suite spanning playground, simulation, batch and live A/B.

Retell AI is a platform for building and running AI voice agents that handle business phone calls, built to be AI native. It lets companies replace traditional interactive voice menus with agents that answer and place calls, sound human, respond with low latency, and carry on natural, multi-turn conversations across voice, and also chat, SMS, and email.

Setup is largely no code. Teams build agents in a visual drag and drop flow builder, defining conversation paths, branching and transfer logic, while the underlying language model handles the conversational reasoning from a high level goal and a few conditions. A proprietary turn-taking model judges when the caller has finished speaking so the agent can respond without awkward pauses, and agents can perform warm transfers or escalate to a human when needed.

Retell handles the telephony as well as the conversation. It connects to existing phone numbers and carriers through SIP trunking or providers like Twilio, supports branded and verified caller ID to reduce spam labeling, and runs outbound batch campaigns.

Agents can call tools, fire webhooks, and pull from connected CRMs, knowledge bases, and other systems, including custom Model Context Protocol servers, and they operate in more than thirty languages with automatic detection of the caller's language.

When an outbound call lands in another company's touch-tone menu, the agent can work out which digits to press and press them, and it detects voicemail and responds to it, both available as nodes in the flow builder.

The platform includes built in testing to simulate conversations and A/B test flows, dashboards tracking outcomes, latency, sentiment, and customer satisfaction, and an automated quality assurance capability that monitors live calls and flags improvements without manual spot checks. Retell is SOC 2, HIPAA and GDPR compliant and supports single sign on.

Retell is used for inbound support, appointment scheduling and confirmations, lead qualification, outbound sales follow-ups, and survey calls, across industries like healthcare, financial services, and logistics. Pricing is based on usage.

Vendor details

Canonical URL

https://www.retellai.com

Category

Customer support agent

Company status

independent

Use cases & customers

Target customers

CX leadersdevelopersenterprise

Deployment options

SaaSAPI

In practice

Your call center drowns in routine tier-one calls and your old phone menu frustrates callers. Retell lets you build a no-code voice agent that answers naturally, handles the common requests, and warm-transfers anything complex to a human.

Missed calls are lost leads after hours. A Retell AI receptionist answers every call around the clock, collects the caller's details, logs them to your CRM, and notifies you, turning a missed call into a captured lead.

You need to confirm hundreds of appointments without staff on the phone all day. Retell runs an outbound batch campaign of calls that confirm or reschedule, in the caller's own language, and writes the results back to your system.

Agentic Index coverage score

12.0 / 14 capabilities · 86%

Integrations & Tool Calling Full

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

Workflow Orchestration Full

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

Knowledge Grounding & RAG Full

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

Human Oversight & Guardrails Full

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

Security, Identity & Governance Full

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

Observability & Auditability Full

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

Memory & State Persistence Full

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

Deployment & Data Residency Not documented

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

Prebuilt Agents, Templates & Packs Full

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

Triggers & Channel Coverage Full

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

Model Flexibility & Routing Full

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

APIs, SDKs & MCP Extensibility Full

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

Testing, Debugging & Optimization Full

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

Browser & Computer Use Not documented

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

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Product updates

·Agent capabilityVerified

Retell released Tell-1, an LLM it trained in house for contact center voice agents, which starts speaking right away and reasons silently while its first sentence plays before deciding whether to ask, answer or call a tool. It runs on Retell's own inference stack at $0.035 per minute. Retell reports a 94.4% average on its own vCX benchmark, ranking first on colloquial speech and second on grounding and instruction following.

Bears on: Agent capability

View source
·Agent capabilityVerified

Release 6.2.15 of the Retell SDK adds duplex, a new response engine for Retell LLM agents that pairs the gpt-live-1 realtime speech model with a text LLM backend, an optional backup and a voice prompt of up to 15,000 tokens. In duplex mode, tools always speak after they run. The same release adds an API call to refresh a knowledge base and a way to list the catalog of integration app templates.

Bears on: Agent capability

View source
·Memory / stateVerified

Retell launched contact memory, a per agent setting that has a model rewrite a running brief for each contact after every completed call or SMS chat, which the agent can load at the start of a later conversation with the same number. Flow builders can mark nodes as skippable when memory already covers them, and teams can backfill memory from earlier calls and chats.

Bears on: Agent capability

View source
View all 5 Retell AI updates →Tracked since Jun 2026 · Verified from public vendor sources

Pricing

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.

Usage, billed per connected minute across separately priced components for voice infrastructure, the voice, the LLM and telephony.

Free tierTrial available

Included quota

Pay as you go has no subscription and includes $10 in free credits (roughly 67 to 90 minutes of testing) and 20 concurrent calls. Enterprise adds custom concurrency (50+), compliance documentation, dedicated support and volume discounts.

What is public

The $0.07 a minute starting rate, every component rate, the $10 in free credits, the 20 free concurrent calls, the $8 price of each extra concurrent slot and a usage calculator are all published. Enterprise rates are custom.

Billing mechanics

Retell is modular and metered per minute. Voice infrastructure is $0.055 a minute, and the voice adds $0.015 a minute for Retell platform voices or $0.08 to $0.10 for premium ElevenLabs voices. The LLM bills separately, from $0.0016 a minute for the lightest model to $0.32 for the most capable ($0.64 on a fast tier), or the customer brings its own. Telephony runs about $0.015 a minute. Failed calls are not billed, and concurrency beyond the free 20 is $8 per call per month.

Cost watchouts

The $0.07 a minute starting rate assumes a platform voice and the lightest model. Premium voices, larger models and telephony stack on top, up to $0.31 a minute at the top of the published range. HIPAA with a BAA requires Enterprise, branded caller ID and international calling add fees, and concurrency slots are a separate monthly line.

Variable cost rationale

Every connected minute is metered, across separately priced components for voice infrastructure, the voice, the LLM and telephony. The bill grows with call minutes, and the model and voice chosen set the rate, from $0.07 a minute at the base to $0.31 at the top of the published range, so identical call volumes can produce very different bills. Concurrency above the included 20 calls adds $8 per call per month, and phone numbers and branded caller ID carry their own fees. No spending cap is published. The configuration is what limits the bill (a lighter model, a platform voice, or the customer's own model), along with the concurrency limit, and calls that fail to connect are not charged. Enterprise sets volume rates by contract.

Additional watchouts

The full component stack (voice, model and telephony) sets the production cost, so the $0.07 starting rate understates what most configurations pay per minute.

Overage / add-ons

Everything is metered per connected minute across components, and calls that fail to connect are not charged. Concurrency beyond the included 20 calls is $8 per concurrent call per month.

Sales call required

Mixed (some tiers require a call)

Free / trial

$10 in free credits and 20 concurrent calls to build and test, no card

Lowest paid plan

Pay as you go at $0.07 to $0.31 per minute for voice agents, with no platform fee

Commercial notes

Developer first voice agent infrastructure, focused on the API and SIP, with a visual builder. There are two tiers, self serve pay as you go and Enterprise. HIPAA with a BAA, SSO and role based access are Enterprise only, and Enterprise adds dedicated infrastructure and volume discounts.

Key ambiguities

Effective per minute cost depends on the model and voice chosen, and Enterprise rates are not published, so total spend is hard to forecast without call data.

Cancellation / refund

Pay as you go has no subscription. Enterprise runs on custom MSA and DPA terms.

Support SLA / resale

Enterprise adds 24/7 omnichannel support through a dedicated portal, HIPAA with a BAA and custom SSO.

Agentic Index verified 2026-07-07

Alternatives to Retell AI

The closest documented capability profiles to Retell AI among customer support agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Gallabox11.5 / 14A lighter documented profile than Retell AI
  • Aisera11.0 / 14A lighter documented profile than Retell AI
  • Botpress11.0 / 14A lighter documented profile than Retell AI
  • Cresta11.0 / 14A lighter documented profile than Retell AI
  • Infobip12.0 / 14Adds documented Deployment & Data Residency
  • Kore.ai13.0 / 14Adds documented Deployment & Data Residency

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.