Agentic Index
Retell AI vs Telnyx (2026)
Both host voice agents that can be built as graphs of nodes with conditions on each step, with tools, transfers and knowledge bases, and they differ on memory, supervision and what sits underneath. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Retell AI keeps a contact record per phone number filled by post call extraction, so the agent recalls preferences and past issues, lets a supervisor listen to a live call and take over, and ships five testing surfaces including batch tests, at $0.07 to $0.31 a minute with voice, model and telephony billed as parts. Telnyx runs on its own carrier network and GPUs. Its voice engine costs $0.05 a minute including speech and knowledge retrieval, models such as Kimi run on Telnyx hardware or on the customer's own endpoint, and voice agents can run in the EU with data kept there. Retell offers no region choice. Choose Retell for caller memory and live supervision out of the box, and Telnyx for EU residency and one supplier from number to model.
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Retell AI and Telnyx 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
- The agent should remember each caller's preferences, past issues and commitments in a contact record.
- A supervisor should listen to a live call silently and take over from the agent.
- Guardrails should catch prohibited topics in what the caller says and in what the agent is about to say.
- Batch tests should run many simulated conversations and judge each against success criteria.
- Outbound calls should work through another company's keypad menu and handle voicemail.
Choose Telnyx if
- Voice agents have to run in the EU with data kept there.
- The model should run on your own OpenAI compatible endpoint, such as Bedrock or a vLLM server.
- Numbers, calls, speech and models should come from one carrier on its own network.
- A new version should take a share of traffic first, with rollback in one step.
| Feature | R Retell AI |
T Telnyx |
|---|---|---|
| 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 |
||
|
TelnyxIntegrations & Tool Calling Assistants call outside systems with webhook tools, which can run asynchronously with filler messages while the request completes, attach MCP servers for whole tool catalogs, and connect enterprise integrations for Salesforce, Zendesk and Jira. Call control tools transfer the caller, hand off with SIP Refer, send DTMF tones to another phone system and hang up, client side tools run actions in the web widget, and keys for outside providers are kept as write only integration secrets. Tools live in a shared library that several assistants and workflow nodes can reuse. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/no-code-voice-assistant.mdread 2026-10-11 |
||
|
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 |
||
|
TelnyxWorkflow Orchestration Conversation workflows store a directed graph on the assistant. Prompt nodes run the model with their own instructions and optional model and voice overrides, speak nodes play a fixed message, and tool nodes run one shared tool and advance. Edges move between nodes on a natural language condition the model judges, a deterministic comparison against variables, or a default, and a tool node's HTTP status code can steer the next edge. An edge can also hand the conversation to another assistant, so a triage assistant can route billing, technical and sales callers to specialists that share the conversation's context. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/workflows.mdread 2026-10-11 |
||
|
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 |
||
|
TelnyxTriggers & Channel Coverage Calls reach an assistant on an assigned Telnyx number or over SIP, outbound calls start from the portal, the API or the TeXML ai_calls endpoint, and an embeddable widget carries voice and chat on a web page. SMS conversations run through the assistant SMS chat API, with MMS during a call when messaging is on. At the start of each conversation a dynamic variables webhook can load caller details and memory settings, and custom SIP headers or the outbound request can pass variables in. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/no-code-voice-assistant.mdread 2026-10-11 |
||
| 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 |
||
|
TelnyxKnowledge Grounding & RAG Each assistant can use named knowledge bases built from uploaded files or a URL, kept with the account and attached in the assistant's configuration, so one knowledge base can serve several assistants. Retrieval during a call is part of the voice engine's orchestration and included in the per minute price, while the price estimator carries a separate agent knowledge base add on. Telnyx does not say how the content is chunked or indexed. Sourcetelnyx.com/pricing/conversational-airead 2026-10-11 |
||
|
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 |
||
|
TelnyxMemory & State Persistence Memory brings earlier conversations into a new one. The dynamic variables webhook returns a query in the same form as the List Conversations endpoint, typically the caller's phone number, a time window or custom metadata, plus the IDs of insights to include, and the assistant starts with those conversations and insight results in context, across voice and messaging. The webhook has one second to answer before the call carries on without memory. What comes back is stored conversation history picked by the customer's query. There is no separate memory store, and Telnyx sets out no retention period or way to delete one person's history. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/memoryread 2026-10-11 |
||
| 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 |
||
|
TelnyxHuman Oversight & Guardrails Transfer and SIP Refer tools pass a caller to a person or another phone system, with voicemail detection on transfer, and handoff tools move a conversation between assistants. Releases stay under the team's control. A new version is saved with notes, traffic rules send selected callers or a percentage to it, and rollback returns all traffic to the main version at once. No step lets a person approve a tool call or a reply before the assistant acts. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/version-testing-traffic-distribution.mdread 2026-10-11 |
||
|
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 |
||
|
TelnyxSecurity, Identity & Governance Business accounts sign in to the Mission Control Portal through SAML single sign on with Okta, Azure Active Directory, Google, OneLogin, Auth0 or LastPass. Telnyx holds ISO 27001:2022 and ISO 27701, a SOC 2 Type II report under NDA covering voice, messaging, video and wireless, and HIPAA coverage for voice, messaging, fax and AI inference with a BAA available, plus PCI DSS for its own billing. The SOC 2 scope does not name AI assistants, and Telnyx also claims a SOC 2 Type III, a report type the AICPA does not issue. Sourcetelnyx.com/ai/compliance.mdread 2026-10-11 |
||
|
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 |
||
|
TelnyxObservability & Auditability Every conversation is stored and listable through the conversations API, transcripts show which workflow node produced each assistant message, and the last tool call's HTTP status is kept as a variable. Insight groups run structured and unstructured analysis on each conversation and can post results to a webhook, with Telnyx managed insights alongside custom ones. Version notes record what changed in each release, and Telnyx does not mention an audit trail of who changed an assistant's configuration. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/workflows.mdread 2026-10-11 |
||
|
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 |
||
|
TelnyxDeployment & Data Residency Voice AI agents run in the United States, the primary data center, or in the European Union with EU data residency, where data does not leave the EU. AI inference is also offered in Asia Pacific with regional processing, though voice agents are not offered there, and Canada has neither. The assistant's language model can also point at the customer's own OpenAI compatible endpoint, such as one on AWS Bedrock, Azure OpenAI or a self run vLLM server, which keeps inference inside an environment the customer controls. Sourcetelnyx.com/ai/compliance.mdread 2026-10-11 |
||
| 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 |
||
|
TelnyxPrebuilt Agents, Templates & Packs New assistants start from a template in the portal, with a blank template as the usual starting point, and Telnyx managed insights come ready to attach to any assistant. A shared tools library lets one set of tools serve many assistants. Telnyx offers no catalog of finished agents for support, sales or scheduling. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/no-code-voice-assistant.mdread 2026-10-11 |
||
| 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 |
||
|
TelnyxModel Flexibility & Routing The customer picks the model for each assistant on the Agent tab. Options include models hosted on Telnyx GPUs, with Kimi as the default, managed third party models from providers such as OpenAI, Gemini and Groq, with OpenAI models on the customer's own key, and any public OpenAI compatible endpoint such as AWS Bedrock, Azure OpenAI, Baseten, vLLM or SGLang. Prompt nodes in a workflow can override the model step by step, and speech to text and text to speech providers are chosen separately. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/custom-llm.mdread 2026-10-11 |
||
|
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 |
||
|
TelnyxAPIs, SDKs & MCP Extensibility The API covers assistants end to end, including creating and updating assistants, assistant tests, canary deploys, MCP server records, SMS chat and a chat endpoint in beta, and the TeXML ai_calls endpoint starts outbound calls. Coding assistants can read the whole reference through llms.txt indexes, and the conversations API hands stored conversations to other systems. Sourcedevelopers.telnyx.com/development/llms/ai-assistants-llms-txtread 2026-10-11 |
||
|
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 |
||
|
TelnyxTesting, Debugging & Optimization AI tests give each check a name, a target assistant and success criteria, such as what the greeting must say, and a test run shows progress live and reports whether the assistant met every criterion, with the conversation to review. A new version can be saved with notes and sent a share of traffic by ordered rules on the caller's number, all to one version or split by percentage, with the remainder staying on the main version, and rollback clears every rule at once. Coval can generate test conversations from seed cases. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/version-testing-traffic-distribution.mdread 2026-10-11 |
||
| 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 |
||
|
TelnyxBrowser & Computer Use Assistants act through webhooks, MCP servers, integrations and call control tools, and send keypad tones to other phone systems. No hosted browser, remote desktop or screen control is offered. Sourcedevelopers.telnyx.com/docs/inference/ai-assistants/tools-library.mdread 2026-10-11 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | R Retell AI |
T Telnyx |
|---|---|---|
|
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 for the voice engine, including speech to text, text to speech and knowledge retrieval, with LLM tokens and telephony extra |
|
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. | Per minute of voice engine time, rounded up to whole minutes per call, plus LLM tokens, per minute telephony and monthly number rental |
|
Variable cost Workload / overage exposure |
High variable cost | High variable cost |
|
Free tier / trial Try before you buy |
Free tierTrial
|
No free tier
|
|
Buying motion Self-serve vs sales call |
Mixed | Mixed |
Retell connects to Telnyx numbers over SIP, so the two can be used together. Retell's HIPAA BAA and dedicated infrastructure sit on its custom Enterprise plan, and Telnyx's Growth and Enterprise plans commit $2,000 and $5,000 a month.
More comparisons with Retell AI or Telnyx
Other matchups in voice agents
Not the pairing you were after? These compare a different set of voice agents on the same 14 capabilities.