At 6 requests/user/day (totaling 9,000,000 queries/mo), running Customer support chatbot on o1-mini costs $36,382.50 / month ($0.7277 / user / mo).
Total expected API invoice for 50,000 Active Users generating 9,000,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 70% cache hits on prompt context.
| Model | Provider | Monthly Spend (50,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| o1-mini (Current) | openai | $36,382.50 | $0.7277 | $436,590.00 | 128,000 |
| GPT-5.6 Terra | openai | $61,110.00 | $1.222 | $733,320.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $76,387.50 | $1.528 | $916,650.00 | 256,000 |
| o3-mini | openai | $36,382.50 | $0.7277 | $436,590.00 | 200,000 |
| o4-mini | openai | $30,318.75 | $0.6064 | $363,825.00 | 256,000 |
| Claude Sonnet 5 | anthropic | $54,810.00 | $1.096 | $657,720.00 | 1,000,000 |
At 6 queries per user/day with o1-mini, the estimated cost is $0.7277 per monthly active user (MAU). Total monthly bill for 50,000 Active Users is $36,382.50.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $12,127.50 per month ($145,530.00/year) on o1-mini.
With a direct COGS of $0.7277 per user/month on o1-mini, charging at least $3.638 per user/month ensures an 80%+ software gross margin.