At 6 requests/user/day (totaling 900,000 queries/mo), running Customer support chatbot on Gemini 2.0 Flash costs $275.625 / month ($0.0551 / user / mo).
Total expected API invoice for 5,000 Active Users generating 900,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 70% cache hits on prompt context.
| Model | Provider | Monthly Spend (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Gemini 2.0 Flash (Current) | $275.625 | $0.0551 | $3,307.50 | 1,048,576 | |
| GPT-5.6 Luna | openai | $611.10 | $0.1222 | $7,333.20 | 1,050,000 |
| GPT-5.4 mini | openai | $2,291.625 | $0.4583 | $27,499.50 | 256,000 |
| GPT-5.4 nano | openai | $626.85 | $0.1254 | $7,522.20 | 128,000 |
| GPT-4o mini | openai | $496.125 | $0.0992 | $5,953.50 | 128,000 |
| Claude Haiku 4.5 | anthropic | $2,740.50 | $0.5481 | $32,886.00 | 1,000,000 |
At 6 queries per user/day with Gemini 2.0 Flash, the estimated cost is $0.0551 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $275.625.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $165.375 per month ($1,984.50/year) on Gemini 2.0 Flash.
With a direct COGS of $0.0551 per user/month on Gemini 2.0 Flash, charging at least $0.2756 per user/month ensures an 80%+ software gross margin.