At 4 requests/user/day (totaling 600,000 queries/mo), running Document summarization on GPT-5.4 Workhorse costs $39,525.00 / month ($7.905 / user / mo).
Total expected API invoice for 5,000 Active Users generating 600,000 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 (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-5.4 Workhorse (Current) | openai | $39,525.00 | $7.905 | $474,300.00 | 256,000 |
| GPT-5.6 Terra | openai | $31,620.00 | $6.324 | $379,440.00 | 1,050,000 |
| o3-mini | openai | $17,259.00 | $3.452 | $207,108.00 | 200,000 |
| o4-mini | openai | $16,846.50 | $3.369 | $202,158.00 | 256,000 |
| o1-mini | openai | $17,259.00 | $3.452 | $207,108.00 | 128,000 |
| Claude Sonnet 5 | anthropic | $30,900.00 | $6.18 | $370,800.00 | 1,000,000 |
At 4 queries per user/day with GPT-5.4 Workhorse, the estimated cost is $7.905 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $39,525.00.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $3,375.00 per month ($40,500.00/year) on GPT-5.4 Workhorse.
With a direct COGS of $7.905 per user/month on GPT-5.4 Workhorse, charging at least $39.525 per user/month ensures an 80%+ software gross margin.