MAG OptiAI

Usage limits

Launch limits for Free Trial and Pro workspaces

Use this page to review the current launch/beta limits that shape MAG OptiAI free trials, paid Pro workspaces, AI credits, saved work, compute usage, and fair-use controls.

Plan summary

What customers should expect during launch

The values below reflect current launch/beta plan limits for customers evaluating Free Trial and Pro access. Enterprise contracts may use manually reviewed terms.

Product limits

Inputs per run

Each workspace has its own input size, row, document, upload, or routing limits.

Saved work

Projects and records

Project, scenario, document, model, storage, and conversation limits are tracked separately from product run size.

AI credits

Separate balance

AI credits are listed separately from product, saved-work, runtime, and fair-use limits.

Product limits

Product input and run-size limits

These limits describe the size of a single product workflow, such as jobs, employees, stops, rows, files, pages, or upload size. Saved projects, scenarios, documents, and AI credits are listed separately below.

SchedAI

Production Scheduling

SchedAI

Free Trial

  • Up to 10 jobs per optimization run
  • Up to 5 machines per optimization run

Pro launch

  • Up to 150 jobs per optimization run
  • Up to 750 operations
  • Up to 50 machines/resources
  • Up to 1,500 precedence, setup, or maintenance rows

Employee Scheduling

SchedAI

Free Trial

  • Up to 15 employees per optimization run
  • Up to 30 shifts per optimization run

Pro launch

  • Up to 150 employees per optimization run
  • Up to 500 shifts
  • Up to 7,500 availability or preference rows

Service Scheduling

SchedAI

Free Trial

  • Up to 20 jobs per optimization run
  • Up to 8 technicians per optimization run

Pro launch

  • Up to 250 visits/jobs per optimization run
  • Up to 75 technicians
  • Up to 300 locations
  • Up to 90,000 travel matrix cells

Academic Scheduling

SchedAI

Free Trial

  • Up to 20 courses
  • Up to 10 rooms
  • Up to 15 instructors per optimization run

Pro launch

  • Up to 250 courses/exams
  • Up to 100 rooms
  • Up to 200 instructors/professors
  • Up to 250 timeslots
  • Up to 7,500 conflict or relationship rows

LogiAI

CVRP Routing

LogiAI

Free Trial

  • Up to 22 stops per optimization run

Pro launch

  • Up to 200 stops per optimization run
  • Up to 50 vehicles

Operational AI

Forecasting

Operational AI

Free Trial

  • Up to 1,000 training rows per dataset

Pro launch

  • Up to 5,000 training rows per dataset

Anomaly Detection

Operational AI

Free Trial

  • Up to 1,000 series rows per scoring run

Pro launch

  • Up to 5,000 series rows per scoring run

Fraud / Risk Scoring

Operational AI

Free Trial

  • Up to 1,000 training rows per dataset

Pro launch

  • Up to 5,000 training rows per dataset
  • Up to 10 MB training upload size

ExtractAI

Operational AI

Free Trial

  • Up to 5 MB upload size

Pro launch

  • Up to 10 MB upload size
  • Up to 25 pages per extraction action

DocAI / Knowledge Assistant

Operational AI

Free Trial

  • Up to 5 MB upload size

Pro launch

  • Up to 100 documents per project
  • Up to 300 documents total
  • Up to 1 GB storage per project
  • Up to 3 GB account storage
  • Up to 2,000 conversation turns per project

AI credits

Included credits by paid product

AI credits are a separate allowance for supported AI actions. The free trial starts with 30 one-time ai credits, low-balance warnings appear at 10 credits or less, paid monthly workspaces receive recurring included credits, and top-up packs can add one-time credits for the active billing period.

Production Scheduling

300 / month

Employee Scheduling

300 / month

Service Scheduling

300 / month

Academic Scheduling

300 / month

CVRP Routing

300 / month

Forecasting

300 / month

Fraud / Risk Scoring

300 / month

Anomaly Detection

300 / month

DocAI / Knowledge Assistant

600 / month

ExtractAI

900 / month

Saved work

Saved work and storage limits

These limits cover what can be saved in a workspace, separate from the size of a single optimization, training, extraction, or DocAI action.

Optimization saved work

Free Trial

  • 3 projects
  • 5 scenarios per project
  • 10 scenarios total
  • 5 scenario versions per scenario

Pro launch

  • 20 projects
  • 50 scenarios per project
  • 200 scenarios total
  • 25 scenario versions per scenario

Forecasting / Fraud / Anomaly saved work

Free Trial

  • 3 projects
  • 2 saved model versions per project
  • 6 saved model versions total
  • 2 datasets per project
  • 5 scoring runs per project
  • 10 scoring runs total

Pro launch

  • 20 projects
  • 25 saved model versions per project
  • 100 saved model versions total
  • 10 datasets per project
  • 50 scoring runs per project
  • 200 scoring runs total

ExtractAI saved work

Free Trial

  • 3 projects
  • 3 documents per project
  • 7 documents total
  • 7 extraction runs per project
  • 10 extraction runs total

Pro launch

  • 20 projects
  • 50 documents per project
  • 200 documents total
  • 100 extraction runs per project
  • 300 extraction runs total

DocAI saved work

Free Trial

  • 3 projects
  • 5 documents per project
  • 10 documents total
  • 25 MB storage per project
  • 50 MB account storage
  • 100 conversation turns per project

Pro launch

  • 20 projects
  • 100 documents per project
  • 300 documents total
  • 1 GB storage per project
  • 3 GB account storage
  • 2,000 conversation turns per project

Retention

Saved-work retention

Retention timing is separate from saved-work capacity. Cleanup language remains cautious because records may be archived, marked for deletion, or queued for cleanup.

Free Trial

Active unused saved work may be archived after 30 days; archived saved work may be deleted after 7 days.

Pro

Active unused saved work may be archived after 90 days; archived saved work may be deleted after 30 days.

Current/protected records

Current, staged, active, or protected state may be excluded from cleanup while needed.

Compute

Runtime and compute usage

These windows help set expectations for how much compute activity a workspace can run during launch.

PlanActive runsMax runtimeDaily windowWeekly window30-day window
Free Trial1120 seconds20 runs / 20 minutes50 runs / 45 minutes150 runs / 2 hours
Pro3300 seconds75 runs / 90 minutes350 runs / 6 hours1,000 runs / 20 hours

Scheduling workspaces

Most scheduling workspaces expose a 300-second maximum runtime control.

CVRP

CVRP exposes a 180-second runtime cap in the Pro Console control surface.

Fair use

Action caps and fair-use controls

These caps help keep launch capacity available across customer workspaces.

Action typePer minutePer dayMonthly reviewConcurrent runsFile sizePages
Core optimization51001,000---
ML training51001,000---
ML prediction/scoring155005,000---
AI assist203003,000---
ExtractAI51001,000210 MB25
DocAI questions153002,0002--

Some actions may pause when minute, daily, concurrency, file-size, or page-count limits are reached. Monthly review thresholds are used to identify unusually heavy usage during launch.

Need help choosing?

Use Pricing for plan selection and Billing for current usage.

Public limits help buyers evaluate fit. Authenticated Pro Console billing and workspace cards remain the best place to review the current account's actual usage, remaining credits, and product-specific status.