At 8 requests/user/day (totaling 120,000 queries/mo), running Agentic workflow on Gemini 3.6 Flash costs $4,338.00 / month ($8.676 / user / mo).
Total expected API invoice for 500 Active Users generating 120,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 65% cache hits on prompt context.
| Model | Provider | Monthly Spend (500 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Gemini 3.6 Flash (Current) | $4,338.00 | $8.676 | $52,056.00 | 1,000,000 | |
| GPT-5.6 Terra | openai | $6,144.00 | $12.288 | $73,728.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $7,680.00 | $15.36 | $92,160.00 | 256,000 |
| o3-mini | openai | $4,356.00 | $8.712 | $52,272.00 | 200,000 |
| o4-mini | openai | $3,498.00 | $6.996 | $41,976.00 | 256,000 |
| o1-mini | openai | $4,356.00 | $8.712 | $52,272.00 | 128,000 |
At 8 queries per user/day with Gemini 3.6 Flash, the estimated cost is $8.676 per monthly active user (MAU). Total monthly bill for 500 Active Users is $4,338.00.
Assuming a 65% cache hit rate on repeated system and context tokens, prompt caching saves $4,212.00 per month ($50,544.00/year) on Gemini 3.6 Flash.
With a direct COGS of $8.676 per user/month on Gemini 3.6 Flash, charging at least $43.38 per user/month ensures an 80%+ software gross margin.