Skip to main content
The Recepta.ai API gives you programmatic access to calls, contacts, and SMS. Everything is scoped to the workspace the API key belongs to.

​
Base URL

All requests must be over HTTPS. Request and response bodies are JSON.

​
Quick start

Build a working integration

A full worked example — create a contact, trigger a call, and verify the webhook that reports the result.
1

Create an API key

In the dashboard, go to API keys and create one with only the permissions you need. Copy it — it’s shown once. See Authentication.
2

Make a request

3

Handle the envelope

Every response carries success and message, with payload under data. See below.

​
Response shape

Successful responses:
Failures use the same envelope with success: false and an appropriate status code:
Branch on the HTTP status code and on success — not on the text of message, which is written for humans and may change.

​
Endpoints

Calls

List, search, retrieve, trigger, and delete calls. Transcripts and recordings.

Contacts

Full CRUD over your contact records.

SMS

Send messages and read conversations.

​
Conventions

List endpoints take page (default 1) and limit (default 50, or 20 on some endpoints). Request one page at a time rather than a very large limit.
Send phone numbers in E.164 format — +14155551234. Numbers submitted when creating a contact are normalized to E.164 automatically; elsewhere, send them already formatted.
ISO 8601, UTC. Date filters accept YYYY-MM-DD.
Pass x-location-id to scope a request to one location. Omit it to cover the whole workspace.

​
Also available

Webhooks

Receive events as they happen instead of polling.

MCP server

Let an AI assistant query your workspace directly.