At 6 requests/user/day (totaling 9,000 queries/mo), running Customer support chatbot on Claude Sonnet 5 costs $54.81 / month ($1.096 / user / mo).
Total expected API invoice for 50 Active Users generating 9,000 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 (50 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Claude Sonnet 5 (Current) | anthropic | $54.81 | $1.096 | $657.72 | 1,000,000 |
| GPT-5.6 Terra | openai | $61.11 | $1.222 | $733.32 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $76.388 | $1.528 | $916.65 | 256,000 |
| o3-mini | openai | $36.383 | $0.7277 | $436.59 | 200,000 |
| o4-mini | openai | $30.319 | $0.6064 | $363.825 | 256,000 |
| o1-mini | openai | $36.383 | $0.7277 | $436.59 | 128,000 |
At 6 queries per user/day with Claude Sonnet 5, the estimated cost is $1.096 per monthly active user (MAU). Total monthly bill for 50 Active Users is $54.81.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $39.69 per month ($476.28/year) on Claude Sonnet 5.
With a direct COGS of $1.096 per user/month on Claude Sonnet 5, charging at least $5.481 per user/month ensures an 80%+ software gross margin.