Pay once, own the deployment.
One-time pricing on every plan. No subscription, no auto-renew. You own the trained dataset and the playbook.
Quickstart
A single-channel chatbot trained on your FAQs and one document.
- Up to 25 FAQ pairs
- 1 knowledge document (PDF / DOCX / TXT)
- Single channel: website widget
- OpenAI GPT-4o mini + Pinecone starter index
- Conversation logs (7 days)
- + 1 more feature →
Spark
A roomier chatbot with custom tone and a real analytics view.
- Up to 75 FAQ / intent pairs
- 5 knowledge documents
- Choose 1 channel: Website OR WhatsApp
- Custom tone & persona configuration
- Conversation analytics (45 days)
- + 2 more features →
Growth
A multi-channel knowledge bot with website crawling and human handoff.
- Up to 200 FAQ / intent pairs
- Full website ingestion (up to 100 pages)
- Up to 10 knowledge documents
- Choose 2 channels (Website / WhatsApp / Slack)
- Configured handoff to email or Slack channel
- + 3 more features →
Pro
Three channels, advanced analytics, and a tested escalation flow.
- Up to 500 FAQ / intent pairs
- Website + helpdesk ingestion (up to 250 pages)
- Up to 25 knowledge documents
- All 3 channels (Website + WhatsApp + Slack)
- Tone QA review on first 100 conversations
- + 4 more features →
Scale
White-glove enterprise rollout with custom integrations.
- Unlimited FAQ / intent pairs
- Unlimited knowledge documents
- All channels + custom API integration
- Multilingual support (up to 5 languages)
- Custom CRM / helpdesk integrations
- + 5 more features →
Side-by-side comparison
Everything that ships with each plan.
| Plan |
Quickstart
$9.99
|
Spark
$13.00
|
Growth
$98.00
|
Pro
$99.00
|
Scale
$119.00
|
|---|---|---|---|---|---|
| Channels included | Website widget | Website widget · WhatsApp (optional) | Website widget · WhatsApp · Slack | Website widget · WhatsApp · Slack | Website widget · WhatsApp · Slack · Custom API |
| Knowledge documents | 1 knowledge document (PDF / DOCX / TXT) | 5 knowledge documents | Up to 10 knowledge documents | Up to 25 knowledge documents | Unlimited knowledge documents |
| Analytics retention | — | Conversation analytics (45 days) | Conversation analytics (90 days) | Advanced analytics (180 days) | — |
| Human handoff | — | — | Yes | — | — |
| Support SLA | Email support within 48 hours | Email support within 24 hours | Priority email + chat support | Priority support within 8 hours | Multilingual support (up to 5 languages) |
Common pricing questions
If yours isn't here, see the full FAQ or contact us.
You get a fully trained, deployed AI chatbot on your chosen channel(s), the underlying training dataset, an analytics dashboard, and a PDF admin guide. Larger plans include human handoff configuration and dedicated specialist time.
Most plans go live in 7–14 business days. Quickstart typically launches within 5 days. Scale (enterprise) takes 3–6 weeks because of the integrations and multilingual setup.
No. We provision and manage the underlying infrastructure as part of the engagement. If you prefer your own keys for compliance reasons, we can BYO on the Scale plan.
Website widget, WhatsApp Business API, Slack, and a REST API for custom integrations (mobile apps, Discord, Microsoft Teams). Channel availability depends on your plan.
PDFs, DOCX, TXT, Markdown, Notion exports, Google Docs, your website (we crawl it), Zendesk macros, or a structured FAQ list. We handle de-duplication and chunking.
We set up a re-ingestion schedule (weekly, monthly, or on-demand) and stamp every chunk with a freshness date. Quarterly retraining is included on Pro and above.
Yes — and it should. Every plan ships with a confidence threshold tuned during evaluation. Below the threshold, the bot offers a handoff instead of inventing an answer.
No. We use the OpenAI API in zero-retention mode (data is not stored or used for model training). Embeddings live in your isolated vector index.
All payments are processed through Authorize.Net using 256-bit SSL encryption. We never store your full card number — Authorize.Net tokenises it at the moment of checkout.
Yes, on the Pro plan and above. We run a redaction layer before the LLM call and substitute redacted values back in the rendered response if needed.