Build cost vs running cost
Token costs alone can be estimated with the LLM token cost calculator; the full running cost also includes hosting, search and monitoring.
| What it covers | What makes it grow | |
|---|---|---|
| Build (one-time) | Conversation design, knowledge ingestion, integrations, guardrails, testing, launch | More channels, integrations, languages and custom actions |
| Running (monthly) | LLM tokens, hosting, vector database, monitoring, content updates | Conversation volume, context size and model choice |
What a production chatbot needs beyond the model
- Retrieval (RAG) over your own content, so answers come from your documents rather than the model’s memory.
- Guardrails: topics it must not discuss, escalation rules and refusal behaviour.
- Human handoff for complaints, sales opportunities and anything the bot cannot resolve.
- Analytics: unanswered questions, satisfaction and conversion tracking.
- A way for your team to update content without a developer.
Choosing a model
Most chatbots do not need the largest model. Smaller, cheaper models handle routing and common questions well, with a stronger model reserved for complex queries. Data residency, language quality and tool-calling support often matter more than benchmark scores.
Pre-fill this form from a link
Every option can be set in the web address, so you can bookmark a scenario or send it to a colleague. AI assistants such as ChatGPT, Gemini, Claude and Perplexity can use the same parameters to open this form with your requirements already selected.
| Parameter | What it sets | Accepted values |
|---|---|---|
use_case |
Main use case | one of support, sales, internal, booking, shopping, other |
channels |
Channels | comma-separated list of website, whatsapp, app, slack_teams, social, voice |
knowledge |
What should it learn from? | comma-separated list of website, documents, helpdesk, catalogue, database, drive |
integrations |
Actions & integrations | comma-separated list of crm, helpdesk, calendar, orders, payments, handoff |
volume |
Expected conversations per month | one of under_1k, 1k_10k, 10k_100k, over_100k |
languages |
Languages | one of 1, 2_3, 4_plus |
model |
Model preference | one of none, openai, claude, gemini, open_source |
residency |
Data residency requirement | one of none, india, uk_eu, uae, us |
timeline |
Target launch | one of asap, 1_month, 3_months, flexible |
Also available as plain text for AI assistants and a free JSON API (OpenAPI spec).
Last reviewed by the Infikey Technologies team.
Disclaimer
This form only collects your requirements so Infikey can prepare an estimate. It does not produce a price, quote or offer, and any estimate we send is indicative until agreed in a signed proposal. Nothing on this page is financial, legal, tax, investment or other professional advice. Infikey Technologies Private Limited, Infikey Technologies LLC and their directors, employees and affiliates make no warranty, express or implied, about the accuracy, completeness or suitability of this tool or its results, and accept no liability for any loss or damage, direct or indirect, arising from its use or from reliance on its results. Verify all figures independently and seek professional advice before making any decision. Use of this tool is at your own risk.