At 40 requests/user/day (totaling 1,200,000 queries/mo), running AI coding assistant on Amazon Nova Micro costs $613.20 / month ($0.6132 / user / mo).
Total expected API invoice for 1,000 Active Users generating 1,200,000 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 (1,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Amazon Nova Micro (Current) | amazon | $613.20 | $0.6132 | $7,358.40 | 128,000 |
| GPT-5.6 Luna | openai | $4,204.80 | $4.205 | $50,457.60 | 1,050,000 |
| GPT-5.4 mini | openai | $15,768.00 | $15.768 | $189,216.00 | 256,000 |
| GPT-5.4 nano | openai | $4,324.80 | $4.325 | $51,897.60 | 128,000 |
| GPT-4o mini | openai | $2,952.00 | $2.952 | $35,424.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $18,624.00 | $18.624 | $223,488.00 | 1,000,000 |
At 40 queries per user/day with Amazon Nova Micro, the estimated cost is $0.6132 per monthly active user (MAU). Total monthly bill for 1,000 Active Users is $613.20.
Assuming a 60% cache hit rate on repeated system and context tokens, prompt caching saves $226.80 per month ($2,721.60/year) on Amazon Nova Micro.
With a direct COGS of $0.6132 per user/month on Amazon Nova Micro, charging at least $3.066 per user/month ensures an 80%+ software gross margin.