At 4 requests/user/day (totaling 1,200 queries/mo), running Document summarization on Gemma 2 9B Instruct costs $6.144 / month ($0.6144 / user / mo).
Total expected API invoice for 10 Active Users generating 1,200 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 10% cache hits on prompt context.
| Model | Provider | Monthly Spend (10 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Gemma 2 9B Instruct (Current) | $6.144 | $0.6144 | $73.728 | 8,192 | |
| GPT-5.6 Luna | openai | $6.324 | $0.6324 | $75.888 | 1,050,000 |
| GPT-5.4 mini | openai | $23.715 | $2.372 | $284.58 | 256,000 |
| GPT-5.4 nano | openai | $6.36 | $0.636 | $76.32 | 128,000 |
| GPT-4o mini | openai | $4.707 | $0.4707 | $56.484 | 128,000 |
| Claude Haiku 4.5 | anthropic | $30.90 | $3.09 | $370.80 | 1,000,000 |
At 4 queries per user/day with Gemma 2 9B Instruct, the estimated cost is $0.6144 per monthly active user (MAU). Total monthly bill for 10 Active Users is $6.144.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Gemma 2 9B Instruct.
With a direct COGS of $0.6144 per user/month on Gemma 2 9B Instruct, charging at least $3.072 per user/month ensures an 80%+ software gross margin.