At 200 requests/user/day (totaling 600,000 queries/mo), running Data extraction & tagging on Claude 3.5 Haiku costs $1,387.20 / month ($13.872 / 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 |
|---|---|---|---|---|---|
| Claude 3.5 Haiku (Current) | anthropic | $1,387.20 | $13.872 | $16,646.40 | 200,000 |
| GPT-5.6 Luna | openai | $376.80 | $3.768 | $4,521.60 | 1,050,000 |
| GPT-5.4 mini | openai | $1,413.00 | $14.13 | $16,956.00 | 256,000 |
| GPT-5.4 nano | openai | $384.30 | $3.843 | $4,611.60 | 128,000 |
| GPT-4o mini | openai | $252.00 | $2.52 | $3,024.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $1,734.00 | $17.34 | $20,808.00 | 1,000,000 |
At 200 queries per user/day with Claude 3.5 Haiku, the estimated cost is $13.872 per monthly active user (MAU). Total monthly bill for 100 Active Users is $1,387.20.
Assuming a 20% cache hit rate on repeated system and context tokens, prompt caching saves $172.80 per month ($2,073.60/year) on Claude 3.5 Haiku.
With a direct COGS of $13.872 per user/month on Claude 3.5 Haiku, charging at least $69.36 per user/month ensures an 80%+ software gross margin.