At 4 requests/user/day (totaling 6,000 queries/mo), running Document summarization on QwQ 32B (Reasoner) costs $58.92 / month ($1.178 / user / mo).
Total expected API invoice for 50 Active Users generating 6,000 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 (50 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| QwQ 32B (Reasoner) (Current) | qwen | $58.92 | $1.178 | $707.04 | 128,000 |
| GPT-5.6 Terra | openai | $316.20 | $6.324 | $3,794.40 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $395.25 | $7.905 | $4,743.00 | 256,000 |
| o3-mini | openai | $172.59 | $3.452 | $2,071.08 | 200,000 |
| o4-mini | openai | $168.465 | $3.369 | $2,021.58 | 256,000 |
| o1-mini | openai | $172.59 | $3.452 | $2,071.08 | 128,000 |
At 4 queries per user/day with QwQ 32B (Reasoner), the estimated cost is $1.178 per monthly active user (MAU). Total monthly bill for 50 Active Users is $58.92.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $5.40 per month ($64.80/year) on QwQ 32B (Reasoner).
With a direct COGS of $1.178 per user/month on QwQ 32B (Reasoner), charging at least $5.892 per user/month ensures an 80%+ software gross margin.