At 6 requests/user/day (totaling 900,000 queries/mo), running Customer support chatbot on o4-mini costs $3,031.875 / month ($0.6064 / user / mo).
Total expected API invoice for 5,000 Active Users generating 900,000 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 (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| o4-mini (Current) | openai | $3,031.875 | $0.6064 | $36,382.50 | 256,000 |
| GPT-5.6 Terra | openai | $6,111.00 | $1.222 | $73,332.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $7,638.75 | $1.528 | $91,665.00 | 256,000 |
| o3-mini | openai | $3,638.25 | $0.7277 | $43,659.00 | 200,000 |
| o1-mini | openai | $3,638.25 | $0.7277 | $43,659.00 | 128,000 |
| Claude Sonnet 5 | anthropic | $5,481.00 | $1.096 | $65,772.00 | 1,000,000 |
At 6 queries per user/day with o4-mini, the estimated cost is $0.6064 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $3,031.875.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $1,819.125 per month ($21,829.50/year) on o4-mini.
With a direct COGS of $0.6064 per user/month on o4-mini, charging at least $3.032 per user/month ensures an 80%+ software gross margin.