At 4 requests/user/day (totaling 12,000 queries/mo), running Document summarization on Claude Sonnet 5 costs $618.00 / month ($6.18 / user / mo).
Total expected API invoice for 100 Active Users generating 12,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 10% cache hits on prompt context.
| Model | Provider | Monthly Spend (100 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Claude Sonnet 5 (Current) | anthropic | $618.00 | $6.18 | $7,416.00 | 1,000,000 |
| GPT-5.6 Terra | openai | $632.40 | $6.324 | $7,588.80 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $790.50 | $7.905 | $9,486.00 | 256,000 |
| o3-mini | openai | $345.18 | $3.452 | $4,142.16 | 200,000 |
| o4-mini | openai | $336.93 | $3.369 | $4,043.16 | 256,000 |
| o1-mini | openai | $345.18 | $3.452 | $4,142.16 | 128,000 |
At 4 queries per user/day with Claude Sonnet 5, the estimated cost is $6.18 per monthly active user (MAU). Total monthly bill for 100 Active Users is $618.00.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $54.00 per month ($648.00/year) on Claude Sonnet 5.
With a direct COGS of $6.18 per user/month on Claude Sonnet 5, charging at least $30.90 per user/month ensures an 80%+ software gross margin.