At 15 requests/user/day (totaling 1,125,000 queries/mo), running Translation on Amazon Nova Pro costs $23,793.75 / month ($9.518 / user / mo).
Total expected API invoice for 2,500 Active Users generating 1,125,000 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 (2,500 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Amazon Nova Pro (Current) | amazon | $23,793.75 | $9.518 | $285,525.00 | 300,000 |
| GPT-5.6 Terra | openai | $83,981.25 | $33.593 | $1,007,775.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $104,976.562 | $41.991 | $1,259,718.75 | 256,000 |
| o3-mini | openai | $32,948.438 | $13.179 | $395,381.25 | 200,000 |
| o4-mini | openai | $32,716.406 | $13.087 | $392,596.875 | 256,000 |
| o1-mini | openai | $32,948.438 | $13.179 | $395,381.25 | 128,000 |
At 15 queries per user/day with Amazon Nova Pro, the estimated cost is $9.518 per monthly active user (MAU). Total monthly bill for 2,500 Active Users is $23,793.75.
Assuming a 15% cache hit rate on repeated system and context tokens, prompt caching saves $506.25 per month ($6,075.00/year) on Amazon Nova Pro.
With a direct COGS of $9.518 per user/month on Amazon Nova Pro, charging at least $47.588 per user/month ensures an 80%+ software gross margin.