At 200 requests/user/day (totaling 60,000,000 queries/mo), running Data extraction & tagging on Mistral Large 3 costs $71,700.00 / month ($7.17 / user / mo).
Total expected API invoice for 10,000 Active Users generating 60,000,000 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 (10,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Mistral Large 3 (Current) | mistral | $71,700.00 | $7.17 | $860,400.00 | 1,000,000 |
| GPT-5.6 Sol | openai | $942,000.00 | $94.20 | $11,304,000.00 | 1,050,000 |
| GPT-5.6 Cyber | openai | $2,355,000.00 | $235.50 | $28,260,000.00 | 1,050,000 |
| GPT-5.5 Standard | openai | $942,000.00 | $94.20 | $11,304,000.00 | 512,000 |
| GPT-5.5 Pro | openai | $5,652,000.00 | $565.20 | $67,824,000.00 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $3,168,000.00 | $316.80 | $38,016,000.00 | 1,000,000 |
At 200 queries per user/day with Mistral Large 3, the estimated cost is $7.17 per monthly active user (MAU). Total monthly bill for 10,000 Active Users is $71,700.00.
Assuming a 20% cache hit rate on repeated system and context tokens, prompt caching saves $10,800.00 per month ($129,600.00/year) on Mistral Large 3.
With a direct COGS of $7.17 per user/month on Mistral Large 3, charging at least $35.85 per user/month ensures an 80%+ software gross margin.