At 6 requests/user/day (totaling 1,800,000 queries/mo), running Customer support chatbot on GPT-4o mini costs $992.25 / month ($0.0992 / user / mo).
Total expected API invoice for 10,000 Active Users generating 1,800,000 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 (10,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-4o mini (Current) | openai | $992.25 | $0.0992 | $11,907.00 | 128,000 |
| GPT-5.6 Luna | openai | $1,222.20 | $0.1222 | $14,666.40 | 1,050,000 |
| GPT-5.4 mini | openai | $4,583.25 | $0.4583 | $54,999.00 | 256,000 |
| GPT-5.4 nano | openai | $1,253.70 | $0.1254 | $15,044.40 | 128,000 |
| Claude Haiku 4.5 | anthropic | $5,481.00 | $0.5481 | $65,772.00 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $4,384.80 | $0.4385 | $52,617.60 | 200,000 |
At 6 queries per user/day with GPT-4o mini, the estimated cost is $0.0992 per monthly active user (MAU). Total monthly bill for 10,000 Active Users is $992.25.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $330.75 per month ($3,969.00/year) on GPT-4o mini.
With a direct COGS of $0.0992 per user/month on GPT-4o mini, charging at least $0.4961 per user/month ensures an 80%+ software gross margin.