Cost Calculation

Mandala automatically calculates costs for all workflow executions, providing transparent pricing based on AI model usage and execution charges. Understanding these costs helps you optimize workflows and manage your budget effectively.

How Costs Are Calculated

Every workflow execution includes two cost components:

Base Execution Charge: $0.001 per execution

AI Model Usage: Variable cost based on token consumption

modelCost = (inputTokens × inputPrice + outputTokens × outputPrice) / 1,000,000
totalCost = baseExecutionCharge + modelCost

AI model prices are per million tokens. The calculation divides by 1,000,000 to get the actual cost. Workflows without AI blocks only incur the base execution charge.

Model Breakdown in Logs

For workflows using AI blocks, you can view detailed cost information in the logs:

The model breakdown shows:

Token Usage: Input and output token counts for each model
Cost Breakdown: Individual costs per model and operation
Model Distribution: Which models were used and how many times
Total Cost: Aggregate cost for the entire workflow execution

Pricing Options

Hosted Models - Mandala provides API keys with a 2.5x pricing multiplier:

Model	Base Price (Input/Output)	Hosted Price (Input/Output)
GPT-4o	$2.50 / $10.00	$6.25 / $25.00
GPT-4.1	$2.00 / $8.00	$5.00 / $20.00
o1	$15.00 / $60.00	$37.50 / $150.00
o3	$2.00 / $8.00	$5.00 / $20.00
Claude 3.5 Sonnet	$3.00 / $15.00	$7.50 / $37.50
Claude Opus 4.0	$15.00 / $75.00	$37.50 / $187.50

The 2.5x multiplier covers infrastructure and API management costs.

Your Own API Keys - Use any model at base pricing:

Provider	Models	Input / Output
Google	Gemini 2.5	$0.15 / $0.60
Deepseek	V3, R1	$0.75 / $1.00
xAI	Grok 4, Grok 3	$5.00 / $25.00
Groq	Llama 4 Scout	$0.40 / $0.60
Cerebras	Llama 3.3 70B	$0.94 / $0.94
Ollama	Local models	Free

Pay providers directly with no markup

Pricing shown reflects rates as of September 10, 2025. Check provider documentation for current pricing.

Cost Optimization Strategies

Usage Monitoring

Monitor your usage and billing in Settings → Subscription:

Current Usage: Real-time usage and costs for the current period
Usage Limits: Plan limits with visual progress indicators
Billing Details: Projected charges and minimum commitments
Plan Management: Upgrade options and billing history

Programmatic Usage Tracking

You can query your current usage and limits programmatically using the API:

Endpoint:

GET /api/users/me/usage-limits

Authentication:

Include your API key in the X-API-Key header

Example Request:

curl -X GET -H "X-API-Key: YOUR_API_KEY" -H "Content-Type: application/json" https://mandala.ayantram.com/api/users/me/usage-limits

Example Response:

{
  "success": true,
  "rateLimit": {
    "sync": { "isLimited": false, "requestsPerMinute": 25, "maxBurst": 25, "remaining": 25, "resetAt": "2025-09-08T22:51:55.999Z" },
    "async": { "isLimited": false, "requestsPerMinute": 200, "maxBurst": 200, "remaining": 200, "resetAt": "2025-09-08T22:51:56.155Z" },
    "authType": "api"
  },
  "usage": {
    "currentPeriodCost": 12.34,
    "limit": 20,
    "plan": "pro"
  },
  "storage": {
    "usedBytes": 104857600,
    "limitBytes": 1073741824,
    "percentUsed": 9.77
  }
}

Response Fields:

rateLimit.sync/rateLimit.async report requestsPerMinute (sustained rate) and maxBurst (burst capacity) separately — there's no single limit field here
currentPeriodCost reflects usage in the current billing period
usage.limit is your included-usage dollar amount for the current plan (see Plan Limits above)
plan is the highest-priority active plan associated with your user
storage reports file/knowledge-base storage usage, separate from execution cost usage

Plan Limits

Different subscription plans have different usage limits:

Plan	Included Usage	Rate Limits (per minute)
Free	$20 (no overage — hard cap)	10 sync, 50 async
Pro	$20/seat included, then overage billed	25 sync, 200 async
Team	$40/seat included (pooled), then overage billed	75 sync, 500 async
Enterprise	$200/seat included by default, custom by agreement	150 sync, 1000 async (defaults, customizable)

These are the platform defaults. See Billing Model below for how included usage and overage actually interact — the numbers above are consistent with it, unlike an earlier version of this table.

Billing Model

Mandala uses a base subscription + overage billing model:

How It Works

Pro Plan ($20/month):

Monthly subscription includes $20 of usage
Usage under $20 → No additional charges
Usage over $20 → Pay the overage at month end
Example: $35 usage = $20 (subscription) + $15 (overage)

Team Plan ($40/seat/month):

Pooled usage across all team members
Overage calculated from total team usage
Organization owner receives one bill

Enterprise Plans:

Fixed monthly price, no overages
Custom usage limits per agreement

Threshold Billing

When unbilled overage reaches $50, Mandala automatically bills the full unbilled amount.

Example:

Day 10: $70 overage → Bill $70 immediately
Day 15: Additional $35 usage ($105 total) → Already billed, no action
Day 20: Another $50 usage ($155 total, $85 unbilled) → Bill $85 immediately

This spreads large overage charges throughout the month instead of one large bill at period end.

Cost Management Best Practices

Monitor Regularly: Check your usage dashboard frequently to avoid surprises
Set Budgets: Use plan limits as guardrails for your spending
Optimize Workflows: Review high-cost executions and optimize prompts or model selection
Use Appropriate Models: Match model complexity to task requirements
Batch Similar Tasks: Combine multiple requests when possible to reduce overhead

Next Steps

Review your current usage in Settings → Subscription
Learn about Logging to track execution details
Explore the External API for programmatic cost monitoring
Check out workflow optimization techniques to reduce costs

Cost Calculation

Model Selection

Prompt Engineering

Local Models

Caching and Reuse

Batch Processing

On this page