Billing

Usage Tracking

Monitor and analyze your Engrami usage with detailed metrics and reporting.

Usage Dashboard

The usage dashboard provides real-time visibility into your credit consumption across all agents, workflows, and features. Access it from Billing → Usage.

Real-time credit balance
Daily/weekly/monthly usage trends
Breakdown by agent, workflow, and operation type
Cost projections and forecasting

Usage API

Get Usage Summary

curl https://api.engrami.com/api/v1/billing/usage?period=month \
  -H "Authorization: Bearer YOUR_TOKEN"

# Response
{
  "period": {
    "start": "2024-01-01T00:00:00Z",
    "end": "2024-01-31T23:59:59Z"
  },
  "summary": {
    "total_credits_used": 45230,
    "total_api_calls": 12543,
    "total_tokens": 4523000,
    "average_daily_usage": 1459
  },
  "by_category": {
    "agent_chat": 35000,
    "embeddings": 5000,
    "memory_storage": 2230,
    "workflows": 3000
  }
}

Usage by Agent

curl https://api.engrami.com/api/v1/billing/usage/agents?period=month \
  -H "Authorization: Bearer YOUR_TOKEN"

# Response
{
  "agents": [
    {
      "agent_id": "agent_support",
      "agent_name": "Customer Support",
      "credits_used": 25000,
      "api_calls": 5234,
      "tokens_used": 2500000,
      "avg_tokens_per_call": 478
    },
    {
      "agent_id": "agent_research",
      "agent_name": "Research Assistant",
      "credits_used": 15000,
      "api_calls": 2100,
      "tokens_used": 1500000,
      "avg_tokens_per_call": 714
    }
  ]
}

Daily Breakdown

curl https://api.engrami.com/api/v1/billing/usage/daily?start=2024-01-01&end=2024-01-31 \
  -H "Authorization: Bearer YOUR_TOKEN"

# Response
{
  "daily": [
    {
      "date": "2024-01-01",
      "credits_used": 1234,
      "api_calls": 456,
      "tokens": 123400
    },
    {
      "date": "2024-01-02",
      "credits_used": 1567,
      "api_calls": 523,
      "tokens": 156700
    }
    // ... more days
  ]
}

Key Metrics

Credit Consumption

Total Credits Used - Sum of all credit deductions
Burn Rate - Average daily/weekly credit consumption
Days Remaining - Estimated days until credits run out

API Metrics

API Calls - Total requests to agents and workflows
Tokens Processed - Input + output tokens for LLM calls
Latency - Average response time
Error Rate - Percentage of failed requests

Memory Metrics

Storage Used - Total memory storage across all types
Queries - Memory search/retrieval operations
Write Operations - New memories stored

Usage Reports

Export detailed usage reports for accounting and analysis:

# Export usage report as CSV
curl -X POST https://api.engrami.com/api/v1/billing/usage/export \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "period": {
      "start": "2024-01-01",
      "end": "2024-01-31"
    },
    "format": "csv",
    "granularity": "daily",
    "include": ["agents", "workflows", "memory", "integrations"]
  }'

# Response
{
  "export_id": "exp_abc123",
  "status": "processing",
  "download_url": null,
  "estimated_completion": "2024-01-20T10:35:00Z"
}

# Check export status
curl https://api.engrami.com/api/v1/billing/usage/export/exp_abc123 \
  -H "Authorization: Bearer YOUR_TOKEN"

# When complete
{
  "export_id": "exp_abc123",
  "status": "completed",
  "download_url": "https://exports.engrami.com/exp_abc123.csv",
  "expires_at": "2024-01-27T10:35:00Z"
}

Cost Forecasting

Project future costs based on historical usage:

curl https://api.engrami.com/api/v1/billing/forecast?months=3 \
  -H "Authorization: Bearer YOUR_TOKEN"

# Response
{
  "current_balance": 45230,
  "monthly_burn_rate": 15000,
  "forecast": [
    {
      "month": "2024-02",
      "projected_usage": 16500,
      "projected_balance": 28730,
      "confidence": 0.85
    },
    {
      "month": "2024-03",
      "projected_usage": 18150,
      "projected_balance": 10580,
      "confidence": 0.75
    },
    {
      "month": "2024-04",
      "projected_usage": 19965,
      "projected_balance": -9385,
      "confidence": 0.65,
      "alert": "Projected to run out of credits"
    }
  ],
  "recommendation": "Consider purchasing 30,000 credits to maintain service"
}

Cost Optimization Tips

Choose the right model - Use GPT-3.5 for simple tasks, GPT-4 only when needed
Optimize prompts - Shorter prompts reduce token usage
Cache responses - Enable response caching for repeated queries
Set context limits - Limit conversation history length
Use memory efficiently - Consolidate old memories to reduce storage
Monitor anomalies - Set up alerts for unusual usage spikes

Usage Alerts

curl -X POST https://api.engrami.com/api/v1/billing/usage/alerts \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "alerts": [
      {
        "name": "Daily Usage Spike",
        "condition": "daily_usage > 5000",
        "channels": ["email"]
      },
      {
        "name": "Agent Anomaly",
        "condition": "agent_usage > 200% of average",
        "channels": ["slack", "email"]
      },
      {
        "name": "Monthly Budget",
        "condition": "monthly_usage > 50000",
        "channels": ["email", "sms"]
      }
    ]
  }'

Back to Documentation Home