API reference
API reference
A REST API over HTTPS with JSON bodies. Every page here is generated from the OpenAPI contract the API itself serves, so what you read is what it accepts.
- Rate limits
- 120 requests a minute per key, 600 per organization. Rate limits
- Base URL
https://api.myleadsfactory.tech/api- Authentication
Authorization: Bearer vak_...Keys- Errors
- The HTTP status plus a JSON body with an
errorcode. Errors - Lists
- Calls, leads, conversations and logs page by cursor:
limit,cursor,next_cursor. Pagination - OpenAPI
- openapi.json for Postman, Insomnia or a client generator
- Web chat from a browser
- The public chat API, with a publishable key
Build
Assistants An assistant is one agent: its instructions, model, voice, tools and channels. Every call and chat runs on an assistant, and every update creates a new version. 15 endpoints.Knowledge Knowledge bases hold the pages, documents and text an assistant answers from. Sources are revised, approved and published as immutable publications, then attached to assistants. 18 endpoints.Phone numbers Search, buy or import numbers, then attach an assistant so it answers inbound calls on that number. 10 endpoints.Calls Place outbound phone calls, start browser calls, and read every call back with its transcript, costs, recordings and analysis. 8 endpoints.Publishable keys Publishable keys (pk_live_...) let a browser start web chats with one assistant from the origins you allow. They are safe to ship in page source; secret API keys are not. 8 endpoints.Public chat API The versioned API for your own chat interface, in a page or an app: start a conversation with a publishable key, then send messages with the conversation token it returns. It runs the same conversations as the chat widget. 16 endpoints.WhatsApp Connect a WhatsApp Business Account from Meta and assign its numbers to assistants. 7 endpoints.Provider credentials Bring your own provider accounts (model, voice and telephony providers). Secrets are encrypted at rest and never returned. 3 endpoints.Voices and models Discover the voices and models a provider offers, and the registry of everything an assistant can be configured with. 5 endpoints.
Results
Conversations Web chat conversations with their messages, costs and lead. Your team can take one over, reply as a person and hand it back to the assistant. 10 endpoints.Leads The details an assistant captured from a visitor, and the outcome you report back once your team follows up. 3 endpoints.Webhooks Subscribe an HTTPS endpoint to events (calls ending, messages, leads) and inspect every delivery attempt. 6 endpoints.
Monitor
Call analytics Call volume and latency over a time range, per project or assistant. 2 endpoints.Chat analytics Web chat health, quality, the visitor funnel, trends and incidents, with notification subscriptions. 14 endpoints.Alerts Rules that notify you when a metric crosses a threshold. 5 endpoints.Audit log Who changed what in your organization, newest first. 1 endpoint.