At 200 requests/user/day (totaling 600,000 queries/mo), running Data extraction & tagging on Mistral Medium 3.5 costs $2,601.00 / month ($26.01 / user / mo).
Total expected API invoice for 100 Active Users generating 600,000 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 (100 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Mistral Medium 3.5 (Current) | mistral | $2,601.00 | $26.01 | $31,212.00 | 256,000 |
| GPT-5.6 Sol | openai | $9,420.00 | $94.20 | $113,040.00 | 1,050,000 |
| GPT-5.6 Cyber | openai | $23,550.00 | $235.50 | $282,600.00 | 1,050,000 |
| GPT-5.5 Standard | openai | $9,420.00 | $94.20 | $113,040.00 | 512,000 |
| GPT-5.5 Pro | openai | $56,520.00 | $565.20 | $678,240.00 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $31,680.00 | $316.80 | $380,160.00 | 1,000,000 |
At 200 queries per user/day with Mistral Medium 3.5, the estimated cost is $26.01 per monthly active user (MAU). Total monthly bill for 100 Active Users is $2,601.00.
Assuming a 20% cache hit rate on repeated system and context tokens, prompt caching saves $324.00 per month ($3,888.00/year) on Mistral Medium 3.5.
With a direct COGS of $26.01 per user/month on Mistral Medium 3.5, charging at least $130.05 per user/month ensures an 80%+ software gross margin.