At 20 requests/user/day (totaling 300,000 queries/mo), running Content generation on GPT-4o mini costs $246.60 / month ($0.4932 / user / mo).
Total expected API invoice for 500 Active Users generating 300,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 30% cache hits on prompt context.
| Model | Provider | Monthly Spend (500 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-4o mini (Current) | openai | $246.60 | $0.4932 | $2,959.20 | 128,000 |
| GPT-5.6 Luna | openai | $467.04 | $0.9341 | $5,604.48 | 1,050,000 |
| GPT-5.4 mini | openai | $1,751.40 | $3.503 | $21,016.80 | 256,000 |
| GPT-5.4 nano | openai | $485.04 | $0.9701 | $5,820.48 | 128,000 |
| Claude Haiku 4.5 | anthropic | $1,975.20 | $3.95 | $23,702.40 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $1,580.16 | $3.16 | $18,961.92 | 200,000 |
At 20 queries per user/day with GPT-4o mini, the estimated cost is $0.4932 per monthly active user (MAU). Total monthly bill for 500 Active Users is $246.60.
Assuming a 30% cache hit rate on repeated system and context tokens, prompt caching saves $5.40 per month ($64.80/year) on GPT-4o mini.
With a direct COGS of $0.4932 per user/month on GPT-4o mini, charging at least $2.466 per user/month ensures an 80%+ software gross margin.