At 200 requests/user/day (totaling 15,000,000 queries/mo), running Data extraction & tagging on Gemma 4 31B Instruct costs $10,312.50 / month ($4.125 / user / mo).
Total expected API invoice for 2,500 Active Users generating 15,000,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 20% cache hits on prompt context.
| Model | Provider | Monthly Spend (2,500 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Gemma 4 31B Instruct (Current) | $10,312.50 | $4.125 | $123,750.00 | 128,000 | |
| GPT-5.6 Terra | openai | $94,200.00 | $37.68 | $1,130,400.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $117,750.00 | $47.10 | $1,413,000.00 | 256,000 |
| o3-mini | openai | $46,200.00 | $18.48 | $554,400.00 | 200,000 |
| o4-mini | openai | $44,550.00 | $17.82 | $534,600.00 | 256,000 |
| o1-mini | openai | $46,200.00 | $18.48 | $554,400.00 | 128,000 |
At 200 queries per user/day with Gemma 4 31B Instruct, the estimated cost is $4.125 per monthly active user (MAU). Total monthly bill for 2,500 Active Users is $10,312.50.
Assuming a 20% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Gemma 4 31B Instruct.
With a direct COGS of $4.125 per user/month on Gemma 4 31B Instruct, charging at least $20.625 per user/month ensures an 80%+ software gross margin.