Cost Calculation

Pailot records a usage cost for each workflow run so operators can see how expensive a process is. Commercial price for the platform itself is on request — there is no public Free or Pro subscription and no published per-run tariff.

How Run Cost Is Calculated

Every workflow execution includes two measured components:

Base execution charge: $0.005 per run (the platform constant BASE_EXECUTION_CHARGE)

Model usage: token cost for AI blocks

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

Model Breakdown in Logs

For workflows that use AI blocks, the log for a run can show:

• Token usage: input and output token counts for each model
• Cost breakdown: per-model and per-operation figures
• Model distribution: which models ran and how many times
• Total cost: sum for that execution

Bring Your Own Key (BYOK)

Use your own API keys for model providers when the contour is configured that way. Keys are stored encrypted. Only workspace admins can manage them.

Supported Providers

Setup

1. Navigate to Settings → BYOK in your workspace
2. Click Add Key for your provider
3. Enter your API key and save

Cost Optimization Strategies

• Model selection: Match model size to the task. Simple extraction does not need the largest reasoning model.
• Prompt engineering: Shorter, structured prompts use fewer tokens.
• Local models: Use Ollama or VLLM in the contour when a local model is enough.
• Caching and reuse: Store repeated results in variables or files instead of calling a model again.
• Batch processing: Process several items in one request when the block allows it.

Usage Monitoring

The contour can expose current-period usage through the API. Limits and the plan field in the response come from the license the vendor configured — not from a public self-serve catalog.

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://pailot.yourdomain.com/api/users/me/usage-limits

Example response:

{
  "success": true,
  "rateLimit": {
    "sync": {
      "isLimited": false,
      "requestsPerMinute": 25,
      "maxBurst": 50,
      "remaining": 50,
      "resetAt": "2025-09-08T22:51:55.999Z"
    },
    "async": {
      "isLimited": false,
      "requestsPerMinute": 200,
      "maxBurst": 400,
      "remaining": 400,
      "resetAt": "2025-09-08T22:51:56.155Z"
    },
    "authType": "api"
  },
  "usage": {
    "currentPeriodCost": 12.34,
    "limit": 100,
    "plan": "enterprise"
  }
}

Rate limit fields:

• requestsPerMinute: sustained refill rate
• maxBurst: maximum tokens you can accumulate
• remaining: tokens available now (up to maxBurst)

Usage fields:

• currentPeriodCost is measured usage in the current period
• limit and plan reflect the contour license, not a public price list

Commercial Terms

Platform price, included usage, and overage (if any) are agreed with ООО «Профитайзер» (Profitizer). Request terms at pailot.ru.

Next Steps

• Learn about Logging to inspect a run
• Use the External API to query usage programmatically
• Review workflow blocks when a run is more expensive than expected