AI Receptionists
AI Receptionist for Small Business: The 2026 Buying Guide (Real Costs, Integrations and a Test Script)
Short answer: An AI receptionist for a small business is a voice agent that answers your phone, takes a complete message or books a slot, writes the result into your CRM or job board, and transfers to a person when the call needs one. If you are comparing AI receptionist for small business cost or asking what is the cost of an AI receptionist, public November 8, 2026 pricing still clusters in three buckets: about $0.07 to $0.31 per minute on a build platform like Retell (their calculator default is $0.11/min), $0.12 to $0.14 per minute on Bland, or about $1.67 to $3.00 per call on a managed service like Smith.ai (Free after 25 calls is $3.00/call; Pro starts at $150/month for 75 calls). Home-service shops already on Jobber can add Receptionist for $29 per month with 30 conversations included, then $0.79 each, or unlimited on Plus. GoHighLevel Voice AI is $50 per month on AI Employee Growth for 100 Voice AI minutes (Starter at $20 per month has no included Voice AI minutes; Unlimited is $97 per month). Live human coverage from Ruby is sold in minute and chat bundles with published standalone chat plans from $143/month. The sticker rate is not the decision. What decides whether it pays off is calendar booking, CRM write-back, warm transfer, and text follow-up. Test those four before you sign.
Updated November 8, 2026: we re-checked every vendor price below on the official pages, added Jobber Receptionist and GoHighLevel Voice AI to the comparison, and noted Retell's November 2 GPT-Live-1 launch. If you text after a call, FCC 26-67 opt-out changes take effect November 25, 2026 (17 days from this update). For the difference between the search phrases "AI answering service" and "AI receptionist," see AI answering service.
We build and test AI receptionists at Wrk Less, mostly on Retell with n8n behind it. This guide is the checklist we use before we recommend a platform. Vendor prices below were re-checked on November 8, 2026 against each public pricing page.
What does an AI receptionist actually cost per call?
Vendors price in three different ways, so sticker prices don't compare directly.
| Option | Pricing model (public, Nov 8, 2026) | What's not in the headline number |
|---|---|---|
| Retell AI | Pay as you go, $0.07–$0.31/min depending on model and voice. Their calculator's default build comes to $0.11/min | Telephony ($0.015/min on Retell's US Twilio numbers), $2/month per number, add-ons like knowledge base (+$0.005/min). GPT-Live 1 is listed at $0.05/minute plus the backend LLM price per minute |
| Vapi | $0.05/min hosting, plus speech-to-text, LLM and voice at provider cost. Core success package $29/month | Telephony is billed by the provider. The Pro success package is 10% of the Vapi hosting fee with a $999/month minimum |
| Bland AI | $0.14/min (Start, no platform fee) or $0.12/min plus $299/month (Build) | Transferred minutes billed at $0.04–$0.05/min. Warm transfers and the in-call SMS node are listed for Enterprise only |
| Synthflow | Annual enterprise agreement scoped to call volume, telephony, integrations, security and launch support. No free plan, no trial and no per-minute rate published | Scoped per contract |
| Jobber Receptionist | $29 per month add-on for 30 conversations, then $0.79 each. Included with unlimited usage on Plus | A Jobber plan and a dedicated phone number are required. Conversations tagged "no conversation" or "spam" do not count. Help article updated October 28, 2026 |
| GoHighLevel Voice AI | AI Employee Growth $50/month includes 100 Voice AI minutes. Starter $20/month has no included Voice AI minutes (pay-per-use). Unlimited $97/month is unlimited Voice AI subject to fair use | Extra usage is paused by default until Extra Usage is enabled. Phone system charges are separate. Traditional Voice Engine is $0.045/min |
| Smith.ai AI Receptionist | Per call: Free includes 25 calls/mo then $3.00/call. Pro $150/mo for 75 calls at $2.00/call (150-call tier $1.80/call; 300-call tier $1.67/call). Enterprise $500/mo for 300 calls at $1.67/call (500-call tier $1.60/call) | Extra real-call rates on Pro $2.50 / $2.30 / $2.17 by tier; Enterprise extras $2.17 / $2.10 / custom; 10% spam allowance |
| Ruby (live humans) | Phone plans sold as receptionist-minute bundles (ask sales for current minute dollar amounts). Standalone chat plans publish at $143 / $335 / $520 per month for 10 / 30 / 50 chats | Bundled chat added to a virtual receptionist plan publishes at $115 / $268 / $416 (a 20% savings). Larger volumes quoted by sales |
Here's a worked example. Say you get 300 calls a month at an average of 3 minutes. That's 900 minutes. At Retell's default configuration plus Retell telephony (about $0.125/min), usage comes to roughly $113 a month. On Bland's Start plan it's about $126 before telephony. Smith.ai's Enterprise tier still lists $500 a month for 300 calls ($1.67/call), with full-service setup on that tier. The same 300 conversations on Jobber Receptionist would be $29 plus 270 extra conversations at $0.79 which is $213.30 in overage plus $29 for a total of $242.30 (Plus includes unlimited usage instead). Ruby's public page still emphasizes plan sizes more than every phone-plan dollar figure; confirm the live minute rate with sales.
Independent auto repair shops in Orlando and Central Florida have a separate Wrk Less path. Founding 5 is $99/month until you cancel for the first five activated shops, with 100 AI-handled minutes each month, no setup fee and no annual contract. The broader Orlando local pilot on auto repair call capture is $197 for the first month with setup waived. The product playbook is on AI receptionist for auto repair.
Read the billing details too. Retell bills for silence and hold time because the transcriber keeps listening. Its agent fee stops when a call is transferred, but telephony keeps running. Bland charges a separate rate for transferred minutes. Per-call pricing like Smith.ai's rewards short calls, and Smith.ai says spam calls count toward your quota unless you flag them (they offer a 10% spam allowance). Jobber does not count conversations tagged "no conversation" or "spam." Price your real call lengths under each model.
The honest math: at small-business volume, usage costs less than one missed job a month. The real cost is the build: the integrations, the call flow, the testing and the upkeep. That's where cheap setups break. A fuller vendor-by-vendor rate card also lives in AI receptionist pricing 2026.
Which integrations actually matter?
A voice agent that only talks is just a nicer voicemail. We scope these five connections on every AI receptionist build:
- Live calendar availability. The agent should check real open slots and book directly. Texting a booking link is a weaker fallback. Ask the vendor whether the calendar is checked during the call or only after it. Retell's built-in Cal.com tools migrated on October 31, 2026; the booking walkthrough is in how an AI receptionist books appointments.
- CRM write-back. Every call should create or update a contact with a summary, a disposition (booked, callback, spam, existing customer) and the recording link. If your team still has to listen to recordings to find out what happened, the system isn't finished. That handoff is the core of AI receptionist lead capture.
- Call transfer with context. A warm transfer should tell the person picking up who's calling and why before the caller is connected. Find out what happens when nobody answers the transfer. The caller should fall back to a captured callback, not dead air.
- SMS follow-up. A confirmation text after booking and a "sorry we missed you" text after a dropped call recover a lot of leads. They're also where consent rules apply. Read our FCC opt-out breakdown before November 25, 2026 and how 10DLC registration differs from TCPA consent before you turn on automated texting.
- Post-call webhooks. This is the escape hatch. If the platform sends a structured payload when a call ends, you can route it anywhere: your CRM, Slack, a job board, a spreadsheet. We usually send it to n8n. Here's how we decide where that logic lives and how Retell webhooks hand off to a CRM.
If you're only trying to stop losing unanswered calls, start smaller. A narrow missed-call capture flow that collects name, number, service and timing and creates a callback task is often the right first build. Add booking and transfers once that works. After-hours needs its own closed greeting and a transfer path that does not ring an empty desk — see AI receptionist for after hours and after-hours AI call answering.
If ChatGPT ad traffic is part of your plan, the same CRM and phone handoff matters after the click. We cover that in ChatGPT Sponsored Agents: catch the lead after the chat.
Want a cost and integration read on your call volume? Book an AI systems assessment and we will map platform vs managed pricing to your real minutes and CRM.
Does the new voice-model wave change what you should buy?
It changes less than the demos suggest. OpenAI released GPT-Live-1 in its API on September 10, 2026. Retell made GPT-Live-1 available on November 2, 2026 as a full-duplex voice model that talks to the caller directly while a backend text LLM keeps running your prompt, tools and knowledge base. On Retell's pricing page it is listed at $0.05/minute plus the backend LLM price per minute, and only for single-prompt voice agents on paid accounts — not conversation flows, multi-prompt, transfer or chat agents. On September 28, ElevenLabs launched Eleven v4 and v4 Turbo. The company reports about 100 ms median inference latency for Turbo, about 150 ms to first speech, and support for more than 90 languages. Retell's public pricing page still lists ElevenLabs v4 at $0.10/minute and v4 Turbo at $0.08/minute as TTS line items, on top of Retell Voice Infra.
For a buyer, natural-sounding voices are table stakes. We walk through when a swap is worth it in New AI Voice Models Just Dropped. Don't pick a vendor because its demo voice sounded the most human. Pick the one whose booking, transfer and CRM behavior holds up on your calls, and make sure you can change models later without rebuilding. If you already run GoHighLevel, also read when native GHL voice AI is enough before you buy a second stack.
How do you test an AI receptionist before you buy?
Don't rely on the vendor's demo line. Set the agent up on a test number with your real hours, services and calendar, then call it yourself. Here's the scorecard we use before a build goes live. Run each call at least twice, once from a quiet room and once from a car or a loud shop floor.
| # | Test call | Pass looks like | Score (0–2) |
|---|---|---|---|
| 1 | Simple booking: "Can I get in Thursday afternoon?" | Offers real open slots, books it, sends a confirmation text | |
| 2 | Interrupt mid-sentence and change the day | Stops, adjusts and doesn't double-book | |
| 3 | Spell a hard name and read back a phone number | Captures both correctly in the CRM record | |
| 4 | Ask for pricing it wasn't given | Declines to guess and offers a callback or transfer | |
| 5 | "I need to talk to a person" | Warm transfer with context, or a clean callback if nobody answers | |
| 6 | Existing customer with a complaint | Recognizes it isn't a sales call and routes it correctly | |
| 7 | Call after hours | Follows your after-hours rules, not daytime ones | |
| 8 | Silence for 10 seconds, then hang up | Doesn't loop. Logs a dropped call and triggers follow-up | |
| 9 | Spanish or a strong accent (if your callers need it) | Understands, or switches language if configured | |
| 10 | Check the back end afterward | Summary, disposition, recording and cost per call are all visible |
A score of 16 or higher out of 20 is ready for a soft launch. Anything that scores zero on tests 4 or 5 is a dealbreaker. An agent that makes up prices or traps a caller who asked for a human will cost you more than it saves.
We also time the gap between the end of the caller's sentence and the start of the agent's reply. Any delay longer than a normal human pause makes callers start talking over the agent. We check that again after every change to the prompt or model.
What are the red flags when choosing a vendor?
- An annual contract before you've run a single real test call. Several platforms are pay as you go, so you have options.
- You can't export recordings, transcripts or call data. That data is your history. If you leave, it should leave with you.
- No post-call webhook or API. You'll end up stuck with whatever integrations they happen to support.
- "Unlimited" plans with no stated limits on concurrency or call length. Look for the cap. It's usually somewhere in the fine print.
- Transfer is "on the roadmap." If the agent can't hand a call to a person today, it isn't a receptionist.
- No way to see cost per call. You should be able to audit your bill at the call level.
- Nobody owns updates. Hours, services and staff change. Someone has to update the agent's instructions and test them again.
Calls coming in after hours need their own rules. We cover that in our guide to after-hours AI call answering and in AI receptionist for after hours. Holiday exceptions, bilingual lines and local Orlando/Orange County setups are separate posts: holiday hours, bilingual AI receptionist in Spanish, Orlando and Orange County and AI receptionist for electricians.
Should you build on a platform or buy a managed service?
Buy a managed, per-call service if you get under a few hundred calls a month, need little integration and want it running this week. Use a product add-on such as Jobber Receptionist if you already live in that system and the native intake is enough. Build on a platform like Retell if calls need to book into your real calendar, update your CRM, transfer by rule and trigger follow-ups across your other tools. That's the work Wrk Less does: we map the call flow, wire up the integrations, run the scorecard above, and stay on for tuning after launch. The setup path is on Retell AI voice agent setup.
Want a second opinion on your call flow? Book an AI systems assessment and we'll go through where your calls go today, what an AI receptionist should handle, and what it would cost to run at your volume.
Questions people ask
How much does Smith.ai AI receptionist pricing cost in 2026?
As of November 8, 2026 on Smith.ai's public AI Receptionist page, Free includes 25 calls per month then $3.00 per call. Pro starts at $150 per month for 75 calls ($2.00/call), with a 150-call tier at $1.80/call and a 300-call tier at $1.67/call. Enterprise starts at $500 per month for 300 calls ($1.67/call), with a 500-call tier at $1.60/call. Extra real-call rates on Pro are $2.50 / $2.30 / $2.17 by tier and on Enterprise $2.17 / $2.10 / custom. A 10% spam allowance is listed on that page.
How much should a small business budget per month for an AI receptionist?
Usage is usually the small part. At 300 calls a month averaging 3 minutes, per-minute platforms such as Retell or Bland come to roughly $113 to $126 in usage based on their public November 2026 pricing, while a managed per-call service like Smith.ai's Enterprise tier is $500 a month for 300 calls. The same 300 conversations on Jobber Receptionist would be $29 plus 270 extras at $0.79 which totals $242.30 unless you are on Plus. Budget separately for setup, integrations and ongoing tuning, which is where most of the real cost sits.
Is per-call or per-minute pricing better for an AI receptionist?
Per-call pricing is easier to predict and favors longer conversations, while per-minute pricing is cheaper when most calls are short. Per-minute platforms also bill for silence and hold time, and some charge for transferred minutes, so compare both models using your actual average call length and monthly call count. Conversation-based add-ons such as Jobber Receptionist meter a call or a text thread as one conversation, which is a third model to price against your mix of calls and texts.
Can an AI receptionist transfer a caller to a real person?
Yes, most voice platforms support call transfer, but quality varies. A good setup does a warm transfer that tells the staff member who is calling and why, and falls back to a captured callback task if nobody picks up. Some platforms reserve warm transfers for higher tiers, so confirm it on the plan you are buying.
What is the fastest way to tell if an AI receptionist will work for my business?
Set it up on a test number with your real hours, services and calendar, then place about ten scripted calls: a simple booking, an interruption, a hard-to-spell name, a pricing question it should not answer, a request for a human, an after-hours call and a silent hang-up. Check that each call lands correctly in your calendar and CRM afterward.
Do I need a new phone number to use an AI receptionist?
Usually not. Most setups forward unanswered or after-hours calls from your existing business line to the AI agent, or route them through your current phone provider. Jobber Receptionist still requires a Jobber dedicated phone number even if you keep your existing line and forward to it. The right approach depends on your phone system, so review your routing before switching anything on.
What is the cost of an AI receptionist for a small business?
It depends on the pricing model. On November 8, 2026, build platforms such as Retell list about $0.07 to $0.31 per minute (calculator default $0.11/min) and Bland lists $0.12 to $0.14 per minute. Managed services such as Smith.ai list about $1.67 to $3.00 per call. Jobber Receptionist is $29 per month for 30 conversations then $0.79 each. GoHighLevel Voice AI is $50 per month on Growth for 100 Voice AI minutes. Live coverage from Ruby publishes standalone chat plans from $143/month. Usage at small-business volume is usually less than one missed job; the build and integrations are the larger cost.
Is an AI answering service the same as an AI receptionist for a small business?
Usually yes. Vendors and buyers use both phrases for the same kind of voice agent on a business line. "AI answering service" is the older search phrase; "AI receptionist" is the product name most platforms use. The comparison that matters is a live answering service versus AI versus a hybrid, not the label. We unpack that in our [AI answering service](/blog/ai-answering-service) guide.