At 8 requests/user/day (totaling 12,000,000 queries/mo), running Agentic workflow on Gemini 3.5 Flash (OpenRouter) costs $460,800.00 / month ($9.216 / user / mo).
Total expected API invoice for 50,000 Active Users generating 12,000,000 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 (50,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Gemini 3.5 Flash (OpenRouter) (Current) | $460,800.00 | $9.216 | $5,529,600.00 | 1,048,576 | |
| GPT-5.6 Terra | openai | $614,400.00 | $12.288 | $7,372,800.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $768,000.00 | $15.36 | $9,216,000.00 | 256,000 |
| o3-mini | openai | $435,600.00 | $8.712 | $5,227,200.00 | 200,000 |
| o4-mini | openai | $349,800.00 | $6.996 | $4,197,600.00 | 256,000 |
| o1-mini | openai | $435,600.00 | $8.712 | $5,227,200.00 | 128,000 |
At 8 queries per user/day with Gemini 3.5 Flash (OpenRouter), the estimated cost is $9.216 per monthly active user (MAU). Total monthly bill for 50,000 Active Users is $460,800.00.
Assuming a 65% cache hit rate on repeated system and context tokens, prompt caching saves $421,200.00 per month ($5,054,400.00/year) on Gemini 3.5 Flash (OpenRouter).
With a direct COGS of $9.216 per user/month on Gemini 3.5 Flash (OpenRouter), charging at least $46.08 per user/month ensures an 80%+ software gross margin.