Why is bring your own API key a problem for small businesses?

Because the buyer is a shop owner, not a developer. Getting a key means opening a separate account with an AI provider, adding a card, generating the key, pasting it in and then reconciling a second bill every month. The advertised price says $19; the real cost is an afternoon and a second vendor relationship.

How can a chatbot include the AI cost without unlimited risk?

By making the billing unit the work the assistant does. A conversation is up to five bot replies in one thread, so a long back-and-forth counts as more than one, and every plan has a cap: 120 on Starter, 300 on Growth, 600 on Pro. The cost ceiling per customer becomes predictable instead of open ended.

What happened to the unlimited Pro plan?

It was removed. Uncapped usage paired with an included AI cost is a blank cheque, and the only customers who would notice are the most expensive ones. Pro now carries a real number, 600 conversations a cycle, and a genuine power user moves to the Managed tier where pricing is scoped to their actual volume.

Is bring your own key ever the right design?

As an optional override for the small group who need it, usually because procurement or compliance requires their own provider account. Build it as a setting, not as the default path through signup. For most small business buyers, one price that already includes the AI removes the step where they close the tab.

Why we stopped asking for an Anthropic API key

Quick answer

Bring your own API key reads as cost transparency to a developer and as a wall to a shop owner. Replai now covers the AI on every paid plan, priced in conversations of up to five bot replies, capped at 120, 300 and 600 a cycle, with a top-up of 100 more for $9 on Starter, $8 on Growth or $7 on Pro. One price, and no separate token bill.

For a non-technical buyer, bring your own key is not transparency. It is a wall.
A conversation of up to five bot replies makes the cost ceiling per customer predictable.
Caps of 120, 300 and 600 a cycle replaced the old unlimited Pro plan.
Keep bring your own key as an optional power-user override, never as the default.

A glowing emerald key dissolving into particles, with a faint price-tag silhouette emerging where it disappears.

When we launched Replai, every paid plan asked you to bring your own Anthropic API key. The pitch was clean — we don't mark up your tokens. You pay Anthropic directly, at cost.

It was honest. It was also the wrong default.

The problem we missed

Replai's actual customer is a small-business owner. A tuition centre operator. A retail brand running a festive promo. An e-commerce founder who can't keep up with WhatsApp DMs.

None of those people have an Anthropic API key. None of them want to open a console.anthropic.com account, paste in a credit card, generate a key, copy it into our settings, then check an AWS-style billing dashboard every month.

We told them the price was $19/month. The actual time-to-first-reply was: sign up → hit a "paste your API key" wall → realise they need a separate Anthropic account → realise they need a credit card → close the tab.

We were selling to one audience and shipping for another.

How does Replai charge for the AI now?

Replai now covers the AI cost on every paid plan. One price, includes the AI.

This isn't a cosmetic change. The numbers had to work first. Three things let them:

Defined a "conversation" as a billing unit. Up to 5 bot replies in a thread. A longer back-and-forth counts as more than one. This makes the cost ceiling per customer predictable instead of unbounded.
Tightened the caps. Starter is 120 conversations a cycle, Growth is 300, Pro is 600. Sized so LLM spend stays around 20% of net revenue at typical usage.
Added a Conversation Pack overage. +100 conversations any time, at $9 on Starter, $8 on Growth and $7 on Pro. A predictable escape valve for the campaign that pushes a customer over their cap. No surprise bills.

The combination is cleaner than BYOK ever was. The customer has one price to think about. We absorb the AI-cost variance.

What does one AI conversation cost to run?

A typical Replai conversation runs on Claude Haiku and costs us a few cents, including the safety-net classifier that runs on every reply. At a 120-conversation Starter cap, the AI cost stays well under the gross-margin floor we set.

The pricing comment in our source code reads "caps sized to keep LLM spend near 20% of net revenue." That's the design target. It's intentionally conservative — we'd rather under-promise margin than under-deliver service.

The Pro plan used to say unlimited conversations. That's gone. Uncapped usage + Replai-funded AI is a blank cheque, and the only customers who'd notice it are the ones who'd cost us the most money. Pro now has a real number (600/cycle), and a true power user is routed to the Managed tier where pricing is scoped to actual volume.

What we'd say to anyone else building a similar product

If your customer is non-technical, BYOK isn't cost transparency. It's a wall. The technical buyer who likes BYOK is the secondary audience for most SMB AI products — not the primary.

The right place for BYOK isn't pricing. It's a power-user feature for the slim slice of customers who genuinely want to provision their own keys, usually because they have enterprise procurement or compliance constraints. Build it as an optional override, not as the default. Most of your audience just wants to pay one number and have it work.

We learned that the slow way. Hopefully the next team building in this space can skip the lesson.

Frequently asked questions

Why is bring your own API key a problem for small businesses?: Because the buyer is a shop owner, not a developer. Getting a key means opening a separate account with an AI provider, adding a card, generating the key, pasting it in and then reconciling a second bill every month. The advertised price says $19; the real cost is an afternoon and a second vendor relationship.
How can a chatbot include the AI cost without unlimited risk?: By making the billing unit the work the assistant does. A conversation is up to five bot replies in one thread, so a long back-and-forth counts as more than one, and every plan has a cap: 120 on Starter, 300 on Growth, 600 on Pro. The cost ceiling per customer becomes predictable instead of open ended.
What happened to the unlimited Pro plan?: It was removed. Uncapped usage paired with an included AI cost is a blank cheque, and the only customers who would notice are the most expensive ones. Pro now carries a real number, 600 conversations a cycle, and a genuine power user moves to the Managed tier where pricing is scoped to their actual volume.
Is bring your own key ever the right design?: As an optional override for the small group who need it, usually because procurement or compliance requires their own provider account. Build it as a setting, not as the default path through signup. For most small business buyers, one price that already includes the AI removes the step where they close the tab.

Sources

WhatsApp Business crosses 200M MAUs, introduces personalized messages feature, TechCrunch, 2023-06-27
WhatsApp Business app, Meta, 2026-09-08

Keep reading

See it answer your own customers.

Pair your number, paste in what you know, and message it from another phone. Ten minutes, no card.

Start free trial