Reference

A single-page lookup for botts.ai: plan limits, what costs credits, supported file types, channels, data-residency tiers, the widget embed, HTTP tools and secrets, form fields, and an explicit list of what the platform does not do (yet).

Quick-reference tables that pull the hard numbers and rules together in one place. For the "why" and "how," follow the links into the full guides.

Plans and limits

New workspaces choose a plan right after signup. Personal starts with a 1-month free trial (150 starter credits) and Business with a 14-day free trial (1,500 starter credits), no credit card required, one free trial per person. To get the full monthly credits right away, choose Pay now instead, without the trial. Prices are the same number in CHF, EUR, and USD; paying yearly is about 17% cheaper. Enterprise is custom and arranged with sales. The legacy Free and Lite plans are no longer offered to new customers; existing Lite organizations keep their plan.

The Personal plan includes the internal AI chat workspace only. Deployments to external channels (website widget, phone) require Business or higher.

See Team & Billing for plan changes, credit blocks, and auto-recharge.

What costs credits

Everything an agent does is metered in credits. Plan credits are spent first, then purchased credits (earliest-expiring first).

To estimate a monthly bill, the cost calculator takes chat, voice or both, a setup (with or without a knowledge base and tools), a model and your volume, and shows the estimated credits per month and a suggested plan. It is a rough estimate. The models page lists each text model's rates under Show details: Input, Output and Cached, in credits per ~1,000 words.

Supported file types and upload limits

• Maximum 100 MB per file. Larger files are rejected before upload.
• Total upload storage is capped by your plan's Upload storage (MB) limit.

Chat attachments accept a wider set and a smaller size, because they are one-off documents rather than permanent agent knowledge:

All three count towards the same Upload storage (MB) limit. Images are stored downscaled (long edge 1568 px) with camera metadata removed. See Attaching documents and Attaching images.

• A scanned or image-only PDF with no extractable text is accepted but shows as Skipped: it contributes no searchable content. Use a text-based PDF or paste the text as Markdown. See Knowledge Base.

Channels

Full details in Deployments.

Data-residency tiers

Set per organization under Organization → General → Server Location (owner/admin). The tier filters which AI models you can select. Switzerland counts as European but is not part of the EU; a UK company does not count as a European company.

Platform infrastructure, knowledge-base storage, and chat history are in Switzerland (Infomaniak) regardless of tier. Voice telephony uses a US provider (Twilio). Web search, when an agent has it on, sends queries to Staan.ai in France. Appointment booking sends the booker's name, email and chosen time to Cal.com's US-hosted service (a self-hosted Cal.com keeps it in Switzerland). Voice, on the phone and in the website widget, runs on GPT Live 1, a Microsoft Azure OpenAI resource in Sweden Central deployed as a global deployment: audio may be processed in Azure regions worldwide; transcripts are stored in Switzerland. Widget voice is off unless the widget enables it. GPT Live 1 counts as a European server run by a US company, so voice (phone deployments, widget voice and the dashboard voice test) is only available under European server, any company and Global. The stricter tiers refuse it; a phone deployment created earlier keeps running but is flagged. botts.ai does not train models on your data. See the FAQ and data-residency post.

Website widget embed

Each website deployment exposes a single script tag, pasted just before the closing </body> tag:

<script async src="https://api.botts.ai/widget/chat-widget.js?key=YOUR_API_KEY"></script>

• The key is the deployment's API key, prefixed bts_. Your real key is shown in the widget editor's Install section; copy the snippet from there.
• The key is public by design and only works for this deployment's widget. The dashboard can't replace it; a new website deployment gets a new key.
• Works on WordPress, Shopify, Squarespace, Wix, or plain HTML. See Deployments.
• The closed widget is a Bubble (default), a Bubble with message, or a Card with buttons (Chat, and Talk when AI voice is on; visitors can minimise it). Set under Launcher in the widget editor.
• AI voice (optional, set under AI voice): a voice session ends after 10 minutes or 90 seconds of silence; the spoken welcome message is up to 300 characters. See Deployments.

Connections and secrets

Connections let an agent call external systems. Configured under Integrations (Admin/Owner).

• Reference a stored secret anywhere in the URL, headers, or auth with $secret:key_name.
• GET/DELETE send parameters as query string; POST/PUT/PATCH send a JSON body. Path variables like {order_id} are percent-encoded and substituted.
• A 2xx response body is passed to the model, capped at both ends if very large; 4xx/5xx bodies are hidden (the model is told the status plus a hint not to invent data). Return 200 with a JSON body for "not found"-style answers.
• Private, localhost, link-local, and cloud-metadata addresses are blocked, for MCP server URLs too.
• MCP tools are registered as servername__toolname. A server that changes its tool list needs re-approval before the change takes effect.

Scheduled tasks

Personal recurring agent runs, under Scheduled in the sidebar. See Scheduled Tasks.

Form fields

Built-in lead-capture templates (enable per agent under Form / Lead Capture):

Custom fields use the same parameter types as tools: string, number, integer, boolean. One submission is captured per conversation; name/email/phone also fill the contact's empty profile fields. Submissions are viewable and exportable to CSV under each agent's Forms tab. See Agents.

What botts.ai doesn't do (yet)

So you (and any agent trained on these docs) don't assume a capability that isn't there:

• No third-party knowledge-base connectors. Knowledge-base sources are website crawl and file upload only. There is no Google Drive, Notion, Dropbox, SharePoint, or S3 sync. (An MCP server can let an agent query such a system live, which is a different thing from indexing it.)
• No public/customer API. There are no personal API keys or a general REST API for sending messages programmatically. The only keys are the per-deployment widget keys (bts_), which authenticate the embedded chat widget on public channels.
• No self-service booking setup yet. Appointment booking in a Cal.com calendar exists, but botts.ai attaches the tool on request. The Booking Request form collects a requested date; it does not check availability or book anything. For another scheduling system, use a connection to call its API.
• No setting that pins the reply language. Agents reply in the language the user writes or speaks. A phone deployment's Language only sets the greeting and first turns, and a widget's Language only sets the widget's own labels. To pin a language, state it in the system prompt.
• No OAuth for connections yet. Connections authenticate with keys, headers, basic auth, or a login endpoint. Catalogue entries whose only login is OAuth are listed but disabled.
• No interactive voice failover. Phone deployments have no backup model.
• WhatsApp, Telegram, and Email channels are not available yet (Coming soon).
• No SAML or organization-wide single sign-on, and no audit logs at this time. (Individual accounts can sign in with Continue with Google or a passkey.)
• No automatic prompt optimization. Testing grades an agent's replies against your expectations; it does not rewrite the prompt, pick a model, or change the agent in any way.

Need one of these? It's often achievable today with a connection, or worth raising with support.

Things this list used to say

Removed because they now exist, in case you remember them as limits:

Last updated on October 7, 2026