Retell AI vs Vapi on price
With the cheapest picks each lists, a minute costs Retell AI $0.0716 and Vapi $0.0681, before the phone line; with the dearest, $0.795 and $0.1313. At 10,000 minutes a month that comes to $716 on Retell AI and $681 on Vapi, so Vapi is cheaper. Retell AI charges $0.055 a minute for Retell Voice Infra, plus $0.0166 for the cheapest language model and voice it lists (GPT 5 nano and Retell Platform Voices); Vapi charges $0.05 a minute for Vapi hosting, plus $0.0181 for the cheapest speech to text, language model and voice it lists (AssemblyAI, Google and Cartesia).
Part by part
A minute of conversation, as each vendor's pricing page splits it:
| Part | Retell AI | Vapi |
|---|---|---|
| Platform fee | $0.055 (Retell Voice Infra) | $0.05 (Vapi hosting) |
| Speech to text | No separate price listed | $0.00521 (AssemblyAI) to $0.01221 (OpenAI), at the provider's price |
| Language model | $0.0016 (GPT 5 nano) to $0.64 (GPT 6 Astra, fast tier) | $0.006 (Google) to $0.04523 (OpenAI), at the provider's price |
| Voice | $0.015 (Retell Platform Voices) to $0.10 (ElevenLabs v3) | $0.00689 (Cartesia) to $0.02383 (ElevenLabs), at the provider's price |
| Phone line | $0.015 to $0.80 on Retell's numbers; no Retell charge with your own SIP trunk | Free over Vapi telephony or SIP; other carriers at their own price, $0.0055 to $0.014 |
| A minute, before the phone line | $0.0716 to $0.795 | $0.0681 to $0.1313 |
| With a US inbound line | $0.0866 to $0.81 Retell number: United States (Twilio): $0.015 | $0.0681 to $0.1313 Vapi Telephony / SIP: $0 |
The range runs from the cheapest to the dearest option each vendor lists for every part, without add-ons. The US line is the vendor's own where it sells one, otherwise a Twilio local number at Twilio's inbound price; number rental is left out.
What a month costs
| Minutes a month | Retell AI | Vapi |
|---|---|---|
| 100 minutes | $7.16 to $79.50 | $6.81 to $13.13 |
| 1,000 minutes | $71.60 to $795 | $68.10 to $131 |
| 10,000 minutes | $716 to $7,950 | $681 to $1,313 |
| 50,000 minutes | $3,580 to $39,750 | $3,405 to $6,564 |
Each side's cheapest picks on the plan that costs least for that volume, then (smaller) its dearest picks; bold marks the cheaper, before the phone line. Plans with included minutes or a lower rate are counted where they lower the bill; phone number rental, extra concurrency and taxes are left out.
How the language model is billed
- Retell AI sells it by the minute at its own prices, $0.0016 to $0.64 across the 48 models and speed tiers it lists.
- Vapi passes it through at the provider's price with no markup: $0.006 to $0.04523 a minute across the providers in its calculator.
Free credit and calls at once
- Retell AI: The first 20 concurrent calls are free; each further one costs $8.00 a month. New accounts get $10 of free credit.
- Vapi: Usage is prepaid. New accounts get $5 of free credit, one Vapi phone number and 4 concurrent calls. Add-ons: extra concurrent call lines cost $10 a month each, extra organizations $20 a month, and HIPAA-eligible data handling $2,000 a month.
Latency, in each vendor's words
- Retell AI: “The platform features a ~600ms latency (industry-leading responsiveness)”
- Vapi: “<500ms average latency”
These are the vendors' own claims. None says what is timed or under what conditions, and they don't use the same measure, so they can't be ranked against each other; test on your own calls.
Price your own stack
Pick a platform, then its parts and your minutes. The phone line opens on an inbound call to a Twilio US local number at Twilio's price; set it to none for web or app calls.
1,000 minutes a month on Retell AI: $230, or $0.23 a minute on average.
| Part | Per minute | Per month |
|---|---|---|
| Retell voice infra | $0.055 | $55.00 |
| Language model GPT 5.5 | $0.16 | $160 |
| Voice (text to speech) Retell Platform Voices | $0.015 | $15.00 |
| Telephony Your own carrier or SIP trunk | $0 | $0 |
| Total | $0.23 | $230 |
Retell AI or Vapi: quick answers
Is Retell AI cheaper than Vapi?
No. With the cheapest picks each lists, Vapi costs least: $0.0716 a minute on Retell AI and $0.0681 a minute on Vapi, before the phone line. At 1,000, 10,000 and 50,000 minutes a month: Retell AI $71.60, $716 and $3,580; Vapi $68.10, $681 and $3,405.
How much do Retell AI and Vapi cost per minute?
Retell AI: a platform fee of $0.055 (Retell Voice Infra); $0.0716 to $0.795 a minute before the phone line, from its cheapest to its dearest picks. Vapi: a platform fee of $0.05 (Vapi hosting); $0.0681 to $0.1313 a minute before the phone line, from its cheapest to its dearest picks.
What do Retell AI and Vapi include in the price, and what's billed on top?
Retell AI: only its own fee in the rate; language model and voice billed on top; phone line: $0.015 to $0.80 on Retell's numbers; no Retell charge with your own SIP trunk. Vapi: only its own fee in the rate; speech to text, language model and voice billed on top; phone line: free over Vapi telephony or SIP; other carriers at their own price, $0.0055 to $0.014.
How is the language model billed on Retell AI and Vapi?
Retell AI sells it by the minute at its own prices, $0.0016 to $0.64 across the 48 models and speed tiers it lists. Vapi passes it through at the provider's price with no markup: $0.006 to $0.04523 a minute across the providers in its calculator.
Do Retell AI and Vapi give free credit, and how many calls can run at once?
Retell AI: The first 20 concurrent calls are free; each further one costs $8.00 a month. New accounts get $10 of free credit. Vapi: Usage is prepaid. New accounts get $5 of free credit, one Vapi phone number and 4 concurrent calls. Add-ons: extra concurrent call lines cost $10 a month each, extra organizations $20 a month, and HIPAA-eligible data handling $2,000 a month.
Which is faster, Retell AI or Vapi?
Retell AI says “The platform features a ~600ms latency (industry-leading responsiveness)”. Vapi says “<500ms average latency”. None says what is timed or under what conditions, and they don't use the same measure, so the figures can't be ranked against each other.
Each platform in full: Retell AI, Vapi. Every platform side by side: AI voice agent cost per minute.
Other comparisons: Vapi vs ElevenLabs Agents, Vapi vs Bland AI, Retell AI vs Bland AI, Retell AI vs ElevenLabs Agents, Vapi vs Twilio ConversationRelay, Retell AI vs Vapi vs ElevenLabs Agents.
Sources
Read on 7 October 2026:
- retellai.com/pricing
- docs.retellai.com/accounts/billing
- docs.retellai.com/accounts/billing-exceptions
- vapi.ai/pricing
- twilio.com/en-us/voice/pricing/us
- retellai.com/
- vapi.ai/
Show the quoted text
Pay as you go Go live in minutes with $10 in free credits. Full platform access, no commitments. Just build, test, and pay as you scale. $0.07-$0.31 / min for AI Voice Agents
retellai.com/pricing
Cost Per Minute $ 0.230 LLM Cost $ 0.160 /min Retell Voice Infra $ 0.055 /min TTS Cost $ 0.015 /min Telephony Cost $ 0.000 /min Add-ons $ 0.000 /min
retellai.com/pricing. The page's cost estimator as it opens in a browser, with GPT 5.5 and Retell's platform voices picked (read in plain headless Chromium; the static HTML holds a placeholder of $0.11 until the script runs).
Conversation Voice Engine Notes Pricing Retell Voice Infra $0.055/minute
retellai.com/pricing
Text-to-speech Notes Pricing Retell Platform Voices $0.015/minute Minimax Voices $0.015/minute Fish Voices $0.015/minute ElevenLabs Flash $0.040/minute ElevenLabs Multilingual v2 $0.06/minute ElevenLabs v3 $0.10/minute ElevenLabs v3 Conversational $0.08/minute ElevenLabs v4 $0.10/minute ElevenLabs v4 Turbo $0.08/minute Cartesia Voices $0.015/minute OpenAI Voices $0.015/minute Inworld Voices $0.015/minute
retellai.com/pricing
LLM Standard Fast Tier GPT 5.6 Terra Recommended $0.064/minute Claude 5 Sonnet Recommended $0.064/minute GPT 5.5 Recommended $0.16/minute $0.32/minute GPT 5.4 Recommended $0.080/minute $0.16/minute GPT 6.1 Sol $0.064/minute $0.128/minute GPT 6 Astra $0.32/minute $0.64/minute GPT 6 Sol $0.064/minute $0.128/minute GPT 6 Luna $0.0032/minute $0.0064/minute GPT 5.6 Sol $0.128/minute $0.256/minute GPT 5.6 Luna $0.0064/minute GPT 5.4 mini $0.024/minute $0.048/minute GPT 5.4 nano $0.0064/minute GPT 5.2 $0.056/minute $0.112/minute GPT 5.1 $0.04/minute $0.08/minute GPT 5 $0.04/minute $0.08/minute GPT 5 mini $0.008/minute $0.016/minute GPT 5 nano $0.0016/minute GPT 4.1 $0.045/minute $0.0675/minute GPT 4.1 mini $0.0128/minute $0.0192/minute GPT 4.1 nano $0.0032/minute $0.0048/minute Claude 5.5 Opus $0.128/minute Claude 5.5 Sonnet $0.064/minute Claude 5 Opus $0.16/minute Claude 4.6 sonnet $0.08/minute Claude 4.5 haiku $0.025/minute Claude 4.5 sonnet $0.08/minute Gemini 3.8 Flash $0.048/minute Gemini 3.7 Flash $0.048/minute Gemini 3.6 Flash $0.024/minute Gemini 3.5 Flash Lite $0.0096/minute Gemini 3.5 Flash $0.048/minute Gemini 3.1 Flash Lite $0.008/minute Gemini 3.0 Flash $0.016/minute
retellai.com/pricing. The table's columns are Standard, then Fast Tier; a model with one price has an empty Fast Tier cell.
Telephony Pricing Call Rates No Charge for Sip Trunking/Custom Telephony Select Country Country United States (Twilio) United States (Twilio Toll Free) India (Twilio) Australia (Twilio) Germany (Twilio) Spain (Twilio) United Kingdom (Twilio) Mexico (Twilio) France (Twilio) Japan (Twilio) Canada (Twilio) Italy (Twilio) Indonesia (Twilio) Philippines (Twilio) Malaysia (Twilio) Thailand (Twilio) United States (Telnyx) India(Telnyx) Canada(Telnyx) $ 0.015 /min
retellai.com/pricing
<option value="0.015" class="option">United States (Twilio)</option><option value="0.06" class="option">United States (Twilio Toll Free)</option><option value="0.15" class="option">India (Twilio)</option><option value="0.1" class="option">Australia (Twilio)</option><option value="0.1" class="option">Germany (Twilio)</option><option value="0.1" class="option">Spain (Twilio)</option><option value="0.1" class="option">United Kingdom (Twilio)</option><option value="0.05" class="option">Mexico (Twilio)</option><option value="0.06" class="option">France (Twilio)</option><option value="0.28" class="option">Japan (Twilio)</option><option value="0.03" class="option">Canada (Twilio)</option><option value="0.06" class="option">Italy (Twilio)</option><option value="0.4" class="option">Indonesia (Twilio)</option><option value="0.8" class="option">Philippines (Twilio)</option><option value="0.2" class="option">Malaysia (Twilio)</option><option value="0.45" class="option">Thailand (Twilio)</option><option value="0.03" class="option">United States (Telnyx)</option><option value="0.25" class="option">India(Telnyx)</option><option value="0.03" class="option">Canada(Telnyx)</option>
retellai.com/pricing. The page's country menu in its own markup; each value is the per-minute rate the page shows when that country is picked.
Call Agent Add-ons Notes Extras Knowledge Base +$0.005/minute Batch Call +$0.005/dial Branded Call +$0.10/outbound call Advanced Denoising +$0.005/min Safety Guardrails +$0.005/min PII Removal +$0.01/min AI Quality Assurance First 100 minutes free $0.10/min SMS $0.01/Msg
retellai.com/pricing
Monthly Subscription Items Notes Pricing Retell Phone Numbers No Charge for custom phone numbers $2.00/month Retell SMS No charge for custom telephony SMS $20.00/month Concurrency (Active Calls) Free for first 20 concurrency (active calls) $8.00/Concurrency/month Knowledge Base $80/month free value (10 KBs) $8.00/Knowledge Base/month (prorated) Verified Phone Number $10.00/Phone number/month
retellai.com/pricing
Speech-to-speech LLM Notes Pricing GPT Realtime 1.5 $0.345/minute GPT Realtime $0.345/minute GPT Realtime mini $0.07/minute GPT Realtime 2.1 $0.38/minute GPT Realtime 2 $0.38/minute GPT Realtime 2.1 mini $0.07/minute
retellai.com/pricing
How do you calculate the minutes? Each call is tracked to the nearest second. At the end of each billing cycle, we charge based on your total accumulated minutes. No rounding up per call, no inflated bills. Does billing continue after a transfer? Once the call is transferred, the AI voice agent fee stops. Only the telephony fee continues for the remainder of the transferred call. Am I charged during silence or hold time? Yes. Billing covers the entire duration of the call because the speech-to-text engine remains active and listening throughout, even during silence.
retellai.com/pricing
Voice infra : Retell’s conversation voice engine. This is the flat per-minute platform cost of running the real-time call, separate from LLM and telephony costs. LLM : the per-minute cost of the language model your agent uses, which varies by model. Telephony : per-minute call rates and monthly phone number fees for Retell-provided numbers. Custom telephony (SIP trunking) carries no Retell telephony charge.
docs.retellai.com/accounts/billing
Rule 2: LLM Price Scaling for > 4,000 Token Prompt Length When it applies: Agents that use more than 4,000 LLM tokens in their prompts Billing adjustment: Duration is scaled proportionally based on token usage
docs.retellai.com/accounts/billing-exceptions
Scaling Factor = Prompt LLM Tokens ÷ 4,000 Billed Duration = Original Duration × Scaling Factor (rounded up) Example: Call duration: 60 seconds LLM tokens used: 4,800 Scaling factor: 4,800 ÷ 4,000 = 1.2 Billed duration: 72 seconds (12 seconds additional charge)
docs.retellai.com/accounts/billing-exceptions
No Success Package Get started for free, and then pay only for the minutes that run $0 to start Pre-paid, $0.05/min Vapi hosting. Models pass-through at cost Start building $5 free credits to get you started 2 organizations 1 included Vapi phone number 4 concurrent calls
vapi.ai/pricing
Core For builders & early teams $29 / month Pre-paid, auto-renew Models pass-through at cost Contact Sales 2 organizations 5 included Vapi phone numbers 10 concurrent calls
vapi.ai/pricing
Pro For scaling teams in production 10% of Vapi hosting fee $999/mo minimum Models pass-through at cost Contact Sales 10 organizations 10 included Vapi phone numbers 30 concurrent calls
vapi.ai/pricing
Four components: speech-to-text, the language model, text-to-speech, and transport. Each is billed at the provider's listed price with no markup. Vapi's $0.05/min hosting fee is added on top.
vapi.ai/pricing. The answer to the page's question "What exactly is in the per-minute cost?", from the page's own data.
It's a percentage of your Vapi hosting fees, model costs are not included.
vapi.ai/pricing. The answer to the page's question "How is the Pro package price calculated?", from the page's own data.
Transcriber Deepgram $0.0095 - $0.0099/min Intelligence Model OpenAI $0.0077 - $0.0452/min Voice ElevenLabs $0.0146 - $0.0238/min
vapi.ai/pricing. The calculator's default picks.
{"id":"transcriber","label":"Transcriber","providers":[{"value":"deepgram","label":"Deepgram","priceLow":0.00953,"priceHigh":0.00994},{"value":"assemblyai","label":"AssemblyAI","priceLow":0.00521,"priceHigh":0.00747},{"value":"openai","label":"OpenAI","priceLow":0.0118,"priceHigh":0.01221}]
vapi.ai/pricing. The calculator's own data: the per-minute range it shows for each transcriber.
{"id":"model","label":"Intelligence Model","providers":[{"value":"openai","label":"OpenAI","priceLow":0.00774,"priceHigh":0.04523},{"value":"anthropic","label":"Anthropic","priceLow":0.00818,"priceHigh":0.03656},{"value":"google","label":"Google","priceLow":0.006,"priceHigh":0.03329}]
vapi.ai/pricing. The calculator's own data: the per-minute range it shows for each model provider.
{"id":"voice","label":"Voice","providers":[{"value":"elevenlabs","label":"ElevenLabs","priceLow":0.0146,"priceHigh":0.02383},{"value":"vapi","label":"Vapi","priceLow":0.00695,"priceHigh":0.01934},{"value":"cartesia","label":"Cartesia","priceLow":0.00689,"priceHigh":0.01294}]
vapi.ai/pricing. The calculator's own data: the per-minute range it shows for each voice provider.
Transport Fee Network and data transport services (Charged by provider, not Vapi) Vapi Telephony / SIP Vapi Telephony / SIP Free Vapi WebSockets Free Daily WebRTC Free Twilio Inbound $0.008 / min Twilio Outbound $0.014 / min Vonage $0.00814 / min Telnyx $0.0055 / min
vapi.ai/pricing
Your Estimate Hosting Fee 1,000 minutes $50 Transcriber Deepgram $10 Intelligence Model OpenAI $8 - $45 Voice ElevenLabs $15 - $24 Transport Fee Vapi Telephony / SIP $0 Success Package No Success Package $0 Estimated Total $ 82 – $ 129 /mo
vapi.ai/pricing
HIPAA compliance HIPAA eligible data handling. Standard Data Processing Agreement and Business Associate Agreement $2,000 / month Additional concurrency Extra concurrent call lines beyond your package default $10 / line / month Additional organizations Extra workspaces beyond your package default $20 / organization / month
vapi.ai/pricing
Number type To make calls To receive calls Refer from Twilio Local calls $0.0140 / min $0.0085 / min Toll-free calls $0.0140 / min $0.0220 / min Browser/app $0.0040 / min $0.0040 / min SIP interface $0.0040 / min $0.0040 / min
twilio.com/en-us/voice/pricing/us
The platform features a ~600ms latency (industry-leading responsiveness)
retellai.com/
<500ms average latency
vapi.ai/
Prices on this page were checked against the official pricing pages on .