At 10 requests/user/day (totaling 30,000 queries/mo), running RAG / search-augmented answers on GPT-4o mini costs $36.00 / month ($0.36 / user / mo).
Total expected API invoice for 100 Active Users generating 30,000 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 (100 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-4o mini (Current) | openai | $36.00 | $0.36 | $432.00 | 128,000 |
| GPT-5.6 Luna | openai | $44.40 | $0.444 | $532.80 | 1,050,000 |
| GPT-5.4 mini | openai | $166.50 | $1.665 | $1,998.00 | 256,000 |
| GPT-5.4 nano | openai | $45.15 | $0.4515 | $541.80 | 128,000 |
| Claude Haiku 4.5 | anthropic | $207.00 | $2.07 | $2,484.00 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $165.60 | $1.656 | $1,987.20 | 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 100 Active Users is $36.00.
Assuming a 50% cache hit rate on repeated system and context tokens, prompt caching saves $9.00 per month ($108.00/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.