How much does an AI chatbot cost?

A chatbot has two prices: the build, which is scoped work, and the running cost, which is almost entirely model tokens plus messaging fees. The running cost surprises people by being small. Ten thousand support conversations on a cheap model come to roughly $37 in model usage at current list prices.

Prices checked:

The short answer

Stop budgeting for the model and start budgeting for the integrations. At list prices the model is often the cheapest line on the invoice; what costs real money is wiring the bot into your CRM, calendar and order data so it has something true to say.

AI chatbot cost split into model tokens, messaging fees and build.
Cost lineHow it is billedCurrent figure
Model, cheap tierPer million tokens in and outClaude Haiku 4.5: $1 in / $5 out per million
Model, mid tierPer million tokens in and outClaude Sonnet 5: $2 in / $10 out per million
Model, top tierPer million tokens in and outClaude Opus 5: $5 in / $25 out per million
Worked example10,000 support conversations, ~3,700 tokens each~$37 total on Claude Haiku 4.5
Repeated contextCache read vs standard input0.1x the input price on a cache hit
WhatsApp repliesPer delivered message, by categoryFree inside the 24-hour customer service window
WhatsApp outboundPer delivered template messageBilled by recipient country and template category

Sources: Claude API pricing (Anthropic docs) · WhatsApp Business Platform pricing · prices checked: Aug 26, 2026

What you actually pay for

A web chat assistant on your own site

No messaging fees at all, so the running cost is tokens and hosting. At a few thousand conversations a month on a cheap model this lands in the tens of dollars, and the build is where the budget actually goes.

The same assistant on WhatsApp

Replies inside the 24-hour service window are free, so an inbound-led support bot adds very little. Costs appear when you start the conversation yourself with a template, which is billed per delivered message.

Voice AI on a phone number

The most expensive channel, because speech recognition and speech synthesis bill per minute on top of the model. Worth it where the alternative is a missed call, which is exactly the case in the lead-response work we do.

The line people forget

A long system prompt and a big retrieved context ride along on every single message. Caching that repeated block drops it to a tenth of the input price, which matters far more at volume than switching model.

How we scope it

Almost every chatbot quote we are asked to sanity-check has the same shape: a large build number, a vague "plus API costs", and no volume assumptions. That is backwards. The API cost is the one line you can calculate exactly today, and Anthropic publishes a worked example for it: about 3,700 tokens per support conversation, so ten thousand conversations on Haiku 4.5 comes to roughly $37. You can do that arithmetic for your own volume in a minute.

What genuinely varies is everything around the model. Whether the bot can read an order. How many channels it answers on. Whether it has to hand off to a human mid-conversation and keep the context. Whether it works in one language or three. Those decide the build, and they also decide whether the thing is useful, because a chatbot with no access to your data is a FAQ page that types slowly. When we quote, the model line is usually the smallest number in the estimate, and we say so rather than hiding it in a bundle. See the systems this sits inside on the AI chatbots page, and what the messaging side costs in WhatsApp Business API pricing.

← All Pricing

FAQ

Frequently asked

01.How much does an AI chatbot cost per month?

For a web chat assistant, the running cost is dominated by model tokens, and at current list prices ten thousand support conversations on a cheap model is roughly $37. Add messaging fees if you run on WhatsApp and per-minute fees if you run on the phone. The build is scoped separately.

02.Why do chatbot quotes vary so much?

Because the model is rarely the cost. Integrations are. A bot that answers from a help page and a bot that reads your order database, books into your calendar and hands off to a human are the same product only in the marketing copy.

03.How can I reduce the running cost?

Cache the parts of the prompt that never change, which brings them down to a tenth of the input price on repeat, and keep retrieved context tight. Both beat switching to a cheaper model, and neither costs you answer quality.

04.Is a cheaper model good enough for support?

For routing, extraction and answering from retrieved documents, usually yes, and the price gap between tiers is large. We test on your real conversations before recommending one, because the honest answer depends on your questions, not on a benchmark.

05.What does the build itself cost?

It depends on channels, integrations, languages and volume, so we scope it in a free 30-minute audit and return a written estimate split into milestones. There is no menu price, and a quote given without those answers is padding.

Related pages

Which process is costing you the most?

Thirty minutes, free. You leave with a concrete plan for fixing it and the number that process costs you. The plan is yours to keep, even if you build it without us.

Book your free audit