Skip to main content
Agntix is the API for building AI chat and voice agents. One platform, three deployable surfaces:

Chat

Conversational text agents you can embed in a web widget, mobile app, or back-office tool.

Voice

Sub-second TTS / STT pipelines over LiveKit, Twilio, or Telnyx — inbound or outbound.

WhatsApp

Wire any agent to a WhatsApp business number via Twilio.

​
Why Agntix

  • Multi-modal out of the box. Same agent definition runs in chat, voice, and WhatsApp.
  • Production-grade reliability. A unified gateway, durable webhooks, persistent sessions, retry-aware call campaigns.
  • Bring your own model. GPT, Claude, Gemini, plus any OpenAI-compatible endpoint.
  • First-class RAG. Upload documents, get cited answers — no vector DB to manage.
  • Predictable pricing. Per-second voice and per-1k-token chat. See pricing.

​
How this works

All Agntix APIs are served from a single base URL behind the API gateway: 
https://api.agntix.ai
The gateway routes traffic to the appropriate upstream service based on the path prefix. As a customer you only ever talk to api.agntix.ai — internal service URLs are not exposed. You’ll mostly interact with three resources:
  1. Agents — the configuration: prompt, model, tools, voice profile, knowledge store.
  2. Sessions — a single conversation between a user and an agent.
  3. Messages — the turns inside a session.
Real-time updates flow over Server-Sent Events for live UIs and Webhooks for back-office workflows.

​
Where to next

Quickstart

Make your first authenticated call in under five minutes.

Build your first agent

Walkthrough: from API key to a working agent that answers user questions.

API Reference

The full, auto-generated reference for every public endpoint.

SDKs & examples

Copy-paste examples in cURL, Node.js, and Python.

​
Need help?