At 10 requests/user/day (totaling 1,500,000 queries/mo), running RAG / search-augmented answers on GPT-4o mini costs $1,800.00 / month ($0.36 / user / mo).
Total expected API invoice for 5,000 Active Users generating 1,500,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 50% cache hits on prompt context.
| Model | Provider | Monthly Spend (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-4o mini (Current) | openai | $1,800.00 | $0.36 | $21,600.00 | 128,000 |
| GPT-5.6 Luna | openai | $2,220.00 | $0.444 | $26,640.00 | 1,050,000 |
| GPT-5.4 mini | openai | $8,325.00 | $1.665 | $99,900.00 | 256,000 |
| GPT-5.4 nano | openai | $2,257.50 | $0.4515 | $27,090.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $10,350.00 | $2.07 | $124,200.00 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $8,280.00 | $1.656 | $99,360.00 | 200,000 |
At 10 queries per user/day with GPT-4o mini, the estimated cost is $0.36 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $1,800.00.
Assuming a 50% 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 $0.36 per user/month on GPT-4o mini, charging at least $1.80 per user/month ensures an 80%+ software gross margin.