At 6 requests/user/day (totaling 90,000 queries/mo), running Customer support chatbot on Amazon Nova Lite costs $16.537 / month ($0.0331 / user / mo).
Total expected API invoice for 500 Active Users generating 90,000 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 (500 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Amazon Nova Lite (Current) | amazon | $16.537 | $0.0331 | $198.45 | 300,000 |
| GPT-5.6 Luna | openai | $61.11 | $0.1222 | $733.32 | 1,050,000 |
| GPT-5.4 mini | openai | $229.163 | $0.4583 | $2,749.95 | 256,000 |
| GPT-5.4 nano | openai | $62.685 | $0.1254 | $752.22 | 128,000 |
| GPT-4o mini | openai | $49.613 | $0.0992 | $595.35 | 128,000 |
| Claude Haiku 4.5 | anthropic | $274.05 | $0.5481 | $3,288.60 | 1,000,000 |
At 6 queries per user/day with Amazon Nova Lite, the estimated cost is $0.0331 per monthly active user (MAU). Total monthly bill for 500 Active Users is $16.537.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $9.923 per month ($119.07/year) on Amazon Nova Lite.
With a direct COGS of $0.0331 per user/month on Amazon Nova Lite, charging at least $0.1654 per user/month ensures an 80%+ software gross margin.