Understanding how DeepMod tracks and manages your usage helps you stay within plan limits and optimize your content moderation costs. This section explains how usage is measured, what happens when you approach limits, and how notifications keep you informed.

How Usage is Measured

Moderation Runs

Run Calculation: Usage is calculated based on content size, with larger content counting as multiple runs:

• Base measurement: 1,000 characters = 1 moderation run

• Shorter content (under 1,000 characters) = 1 run minimum

• Longer content is divided by 1,000 characters and rounded up

Examples:

• 500-character comment = 1 run

• 1,500-character post = 2 runs

• 3,200-character article = 4 runs

Batch Mode (Policy Chains): When running moderation in batch mode with multiple policies, each policy counts as a separate run:

• Calculation: (Number of policies) × (Content runs) = Total runs

• Each policy in the batch processes the same content independently

• Usage multiplies by the number of policies in the chain

Batch Mode Examples:

• 2 policies, 500-character content = 2 runs (1 per policy)

• 3 policies, 1,500-character content = 6 runs (3 policies × 2 content runs)

• 2 policies, 5,000-character content = 10 runs (2 policies × 5 content runs)

Human Reviews

Review Updates: Human reviews update existing moderation runs rather than creating separate usage:

• Reviews modify the original moderation run that was already counted

• No additional usage is charged for human review decisions

• Reviews are tracked for analytics but don't count toward usage limits

Usage Periods

Monthly Billing Cycles: Usage resets at the start of each billing period based on your subscription start date, not calendar months.

Real-Time Tracking: Usage is updated immediately as runs complete and reviews are submitted.

Plan Limits

Free Plan ($0/month):

• Moderation: 100 runs per month

• Policies: 5 active policies

• Rules per Policy: 25 rules maximum

• Language Model: Uses a smaller, less accurate model than paid tiers

Starter Plan ($599/month):

• Moderation: 5,000 runs per month

• Policies: Unlimited active policies

• Rules per Policy: 100 rules maximum

• Language Model: Full-featured, highly accurate model

Professional Plan ($999/month):

• Moderation: 10,000 runs per month

• Policies: Unlimited active policies

• Rules per Policy: 100 rules maximum

• Language Model: Full-featured, highly accurate model

Enterprise Plan ($1,999/month):

• Moderation: 25,000 runs per month

• Policies: Unlimited active policies

• Rules per Policy: 100 rules maximum

• Language Model: Full-featured, highly accurate model

Optimizing Usage

Reducing Moderation Costs

Content Filtering: Pre-filter obviously acceptable content before sending to DeepMod

Policy Chain Optimization: Carefully consider batch mode usage

• Each policy in a chain multiplies your usage costs

• Use batch mode only when multiple policies are truly necessary

• Consider combining related rules into a single policy instead of chaining multiple policies

Policy Tuning: Adjust confidence thresholds to reduce unnecessary ambiguous results

Managing Review Efficiency

Threshold Optimization: Higher confidence thresholds reduce ambiguous results requiring human review Review Mode Selection: Use "No Review" mode when automated decisions are sufficient Policy Separation: Create different policies with different review settings for different content types

Content Preparation

Clean Input: Remove formatting, extra whitespace, and irrelevant text before moderation Logical Chunking: Split very long content at natural break points (paragraphs, sections) Metadata Usage: Include relevant context to improve moderation accuracy

Monitoring and Analytics

Usage Patterns

Daily Tracking: Monitor day-to-day usage to identify patterns and spikes Content Type Analysis: Track which content types consume the most runs Policy Performance: Identify policies that generate excessive ambiguous results

Forecasting

Trend Analysis: Use historical data to predict future usage needs Seasonal Planning: Account for content volume changes during different periods Growth Planning: Plan plan upgrades based on content growth projections

API Rate Limits

Request Limits

Concurrent Requests: Maximum simultaneous moderation requests vary by plan Rate Limiting: Requests per minute limits to ensure system stability Retry Handling: Implement exponential backoff for rate-limited requests

Best Practices

Request Spacing: Distribute API calls evenly rather than sending bursts Error Handling: Properly handle rate limit responses and retry appropriately Monitoring: Track API response times and success rates

What's Next

• Troubleshooting - Common usage and limit issues and solutions

Effective usage management ensures your content moderation runs smoothly while staying within budget and plan constraints.

Questions about usage or limits? Contact support for help with plan selection, usage optimization, or limit management strategies.