At 40 requests/user/day (totaling 12,000 queries/mo), running AI coding assistant on Amazon Nova Lite costs $10.512 / month ($1.051 / user / mo).
Total expected API invoice for 10 Active Users generating 12,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 60% cache hits on prompt context.
| Model | Provider | Monthly Spend (10 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Amazon Nova Lite (Current) | amazon | $10.512 | $1.051 | $126.144 | 300,000 |
| GPT-5.6 Luna | openai | $42.048 | $4.205 | $504.576 | 1,050,000 |
| GPT-5.4 mini | openai | $157.68 | $15.768 | $1,892.16 | 256,000 |
| GPT-5.4 nano | openai | $43.248 | $4.325 | $518.976 | 128,000 |
| GPT-4o mini | openai | $29.52 | $2.952 | $354.24 | 128,000 |
| Claude Haiku 4.5 | anthropic | $186.24 | $18.624 | $2,234.88 | 1,000,000 |
At 40 queries per user/day with Amazon Nova Lite, the estimated cost is $1.051 per monthly active user (MAU). Total monthly bill for 10 Active Users is $10.512.
Assuming a 60% cache hit rate on repeated system and context tokens, prompt caching saves $3.888 per month ($46.656/year) on Amazon Nova Lite.
With a direct COGS of $1.051 per user/month on Amazon Nova Lite, charging at least $5.256 per user/month ensures an 80%+ software gross margin.