At 4 requests/user/day (totaling 1,200,000 queries/mo), running Document summarization on GPT-4o mini costs $4,707.00 / month ($0.4707 / user / mo).
Total expected API invoice for 10,000 Active Users generating 1,200,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 10% cache hits on prompt context.
| Model | Provider | Monthly Spend (10,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-4o mini (Current) | openai | $4,707.00 | $0.4707 | $56,484.00 | 128,000 |
| GPT-5.6 Luna | openai | $6,324.00 | $0.6324 | $75,888.00 | 1,050,000 |
| GPT-5.4 mini | openai | $23,715.00 | $2.372 | $284,580.00 | 256,000 |
| GPT-5.4 nano | openai | $6,360.00 | $0.636 | $76,320.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $30,900.00 | $3.09 | $370,800.00 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $24,720.00 | $2.472 | $296,640.00 | 200,000 |
At 4 queries per user/day with GPT-4o mini, the estimated cost is $0.4707 per monthly active user (MAU). Total monthly bill for 10,000 Active Users is $4,707.00.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $225.00 per month ($2,700.00/year) on GPT-4o mini.
With a direct COGS of $0.4707 per user/month on GPT-4o mini, charging at least $2.354 per user/month ensures an 80%+ software gross margin.