Home/API Docs

API Reference

Connect directly to our inference endpoints. The Iterate AI platform exposes a high-performance REST API built with FastAPI. All endpoints return JSON.

Primary Regional Endpoint

https://api.iterateai.in

Latency: 42ms

All API calls securely communicate directly with our dedicated FastAPI inference instances for reduced latency and dynamic scaling.

/v1 Endpoints

POST/api/chat

AI chat — send conversation history, receive assistant reply.

POST/api/contact

Contact form — scores lead, sends email, tracks in analytics.

POST/api/search

Semantic site search — returns AI answer + relevant page results.

GET/api/analytics/dashboard

Returns live analytics: KPIs, traffic, lead pipeline.

POST/api/analytics/pageview

Track a page view event.

GET/health

Health check — returns service status, model, and email config.

Need Enterprise API Access?

Unlock custom rate limits, dedicated hardware, direct VPC peering, webhooks, and guaranteed 99.99% SLAs for mission-critical inference.

Direct VPC Peering

Custom Rate Limits

SSO & SAML

Dedicate Hardware

Provision Keys