At 15 requests/user/day (totaling 4,500,000 queries/mo), running Translation on Amazon Nova Micro costs $4,163.906 / month ($0.4164 / user / mo).
Total expected API invoice for 10,000 Active Users generating 4,500,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 15% cache hits on prompt context.
| Model | Provider | Monthly Spend (10,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Amazon Nova Micro (Current) | amazon | $4,163.906 | $0.4164 | $49,966.875 | 128,000 |
| GPT-5.6 Luna | openai | $33,592.50 | $3.359 | $403,110.00 | 1,050,000 |
| GPT-5.4 mini | openai | $125,971.875 | $12.597 | $1,511,662.50 | 256,000 |
| GPT-5.4 nano | openai | $34,830.00 | $3.483 | $417,960.00 | 128,000 |
| GPT-4o mini | openai | $17,971.875 | $1.797 | $215,662.50 | 128,000 |
| Claude Haiku 4.5 | anthropic | $143,212.50 | $14.321 | $1,718,550.00 | 1,000,000 |
At 15 queries per user/day with Amazon Nova Micro, the estimated cost is $0.4164 per monthly active user (MAU). Total monthly bill for 10,000 Active Users is $4,163.906.
Assuming a 15% cache hit rate on repeated system and context tokens, prompt caching saves $88.594 per month ($1,063.125/year) on Amazon Nova Micro.
With a direct COGS of $0.4164 per user/month on Amazon Nova Micro, charging at least $2.082 per user/month ensures an 80%+ software gross margin.