At 200 requests/user/day (totaling 15,000,000 queries/mo), running Data extraction & tagging on GPT-4o mini costs $6,300.00 / month ($2.52 / user / mo).
Total expected API invoice for 2,500 Active Users generating 15,000,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 20% cache hits on prompt context.
| Model | Provider | Monthly Spend (2,500 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-4o mini (Current) | openai | $6,300.00 | $2.52 | $75,600.00 | 128,000 |
| GPT-5.6 Luna | openai | $9,420.00 | $3.768 | $113,040.00 | 1,050,000 |
| GPT-5.4 mini | openai | $35,325.00 | $14.13 | $423,900.00 | 256,000 |
| GPT-5.4 nano | openai | $9,607.50 | $3.843 | $115,290.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $43,350.00 | $17.34 | $520,200.00 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $34,680.00 | $13.872 | $416,160.00 | 200,000 |
At 200 queries per user/day with GPT-4o mini, the estimated cost is $2.52 per monthly active user (MAU). Total monthly bill for 2,500 Active Users is $6,300.00.
Assuming a 20% cache hit rate on repeated system and context tokens, prompt caching saves $450.00 per month ($5,400.00/year) on GPT-4o mini.
With a direct COGS of $2.52 per user/month on GPT-4o mini, charging at least $12.60 per user/month ensures an 80%+ software gross margin.