RXed AI News

AI to the bone.
Audited 2026-08-05 · RXed table v1.0

Retell AI

Visit retellai.com
“Retell is a platform to build, test, deploy, and monitor AI voice and chat agents with telephony, prompts, tools, and analytics built in.” — the vendor’s own words

The developer-first voice stack: real MCP server, real fine-tuning, a live pricing calculator on the homepage — just remember $0.07/min is the floor, not the bill.

The verdict, read by Jan · AI clone of Jan’s voice, generated locally with his consent.
Best for: Engineering teams that want direct, code-level control over a voice agent stack — model choice, prompt iteration, MCP-based tooling — without an enterprise sales cycle or managed-service overhead.
Scope16/20
Quality7/10
Where the quality sits
7Reactive
7Retrieval & Memory
7Orchestration
8Validation
7Models
SpecialistVoice AgentsAutomation & AgentsVoice & SpeechSalesFreemium
Vendor
Retell AI · www.retellai.com
Origin
US — Redwood City, California
Pricing
Pay as you go $0.07-$0.31/min · Enterprise Custom
Users (official only)
3,000+ businesses use Retell's voice agents; 55+ million AI phone calls routed monthly, including customers such as the San Antonio Spurs, Motorola, Lenovo and Anker (source, 2026-06-22)
Pay as you go$0.07-$0.31/min$10 free credits, 20 free concurrent calls, no platform fee or minimum commitment
EnterpriseCustomDedicated stable server, no concurrent call cap, HIPAA/BAA, custom SSO/MSA/DPA, 24/7 support

The advertised rate covers voice infrastructure only ($0.055/min). A realistic setup with TTS, an LLM and telephony stacked on runs $0.11-$0.31/min depending on model choice; this stacked-billing structure is the single most common complaint in independent G2 review round-ups.

checked 2026-08-05 · vendor pricing page

Element scores

Reactive
Retrieval & Memory
Orchestration
Validation
Models
Primitives
Compositions
Deployment
Emerging
Tap or hover any element to see why it got that score.

Strengths

True self-serve, pay-as-you-go pricing with a live cost calculator on the homepage, model-agnostic access to the current frontier LLM lineup (GPT 5.x, Claude 4.6, Gemini 3.x) plus bring-your-own custom model, a working MCP server for managing agents from Cursor or Claude Desktop, and a genuinely deep testing stack — graded regression test sets, live A/B split-testing, and an AI Quality Assurance add-on that auto-scores production calls.

Honest dings

The advertised $0.07/min is voice-infrastructure only; real production cost with LLM, TTS and telephony stacked on runs $0.11-$0.31/min, and G2 reviewers flag this pricing structure as the most common complaint. CRM integrations beyond Cal.com/HubSpot/Salesforce are limited without custom API work, and reported real-world latency (1s+ in some regions) sometimes runs above the ~600-800ms headline benchmark.

Prices and details change — this passport is re-verified at least quarterly.
Sources (11) — every claim traceable

Every audit lists the research it rests on — transparency and traceability are the product. Tools evolve: each audit is a snapshot of its audit date, and re-audits supersede older versions (kept below for reference).