ManticDocs

Overview

Learn how Mantic forecasts work and build a reliable integration with the Mantic API.

Mantic forecasts events in geopolitics, business, policy, technology and culture. The API serves the same forecasts and reasoning you see in the Mantic web app.

For API credentials (a client ID and client secret), ask your Mantic contact or support@mantic.com.

Start here

  • Read your first forecast — get credentials and make your first request.
  • Understand a forecast — interpret probabilities, uncertainty and reasoning.
  • Find forecasts — search by text, browse tags, sort by recent activity or list the forecasts on a dashboard.
  • Read forecasts — handle each forecast type, get the probability above or below a value, read reasoning and compare forecast runs over time.
  • Follow economic releases — find a country's upcoming releases, read the forecast for the next release and compare it with the published actual.
  • Explore scenarios — compare a forecast under two possible outcomes of a related forecast.
  • Create forecasts (beta) — validate one draft, or create forecasts in bulk from a template.
  • Example workflows — build a dashboard briefing, or compare Mantic with prediction markets.
  • API reference — parameters, response schemas and request examples for each endpoint.

Forecasts in the API

A forecast has a definition (its title and resolution criteria) and a history of forecast runs, each with a probability or distribution and its reasoning.

In the API, a forecast is a question (question_id), and each run is a forecast object (forecast_id). These pages say "forecast" and "forecast run" in prose and keep the API names in code; see Understand a forecast.

On this page