At 6 requests/user/day (totaling 18,000,000 queries/mo), running Customer support chatbot on GPT-5.4 nano costs $12,537.00 / month ($0.1254 / user / mo).
Total expected API invoice for 100,000 Active Users generating 18,000,000 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 (100,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-5.4 nano (Current) | openai | $12,537.00 | $0.1254 | $150,444.00 | 128,000 |
| GPT-5.6 Luna | openai | $12,222.00 | $0.1222 | $146,664.00 | 1,050,000 |
| GPT-5.4 mini | openai | $45,832.50 | $0.4583 | $549,990.00 | 256,000 |
| GPT-4o mini | openai | $9,922.50 | $0.0992 | $119,070.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $54,810.00 | $0.5481 | $657,720.00 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $43,848.00 | $0.4385 | $526,176.00 | 200,000 |
At 6 queries per user/day with GPT-5.4 nano, the estimated cost is $0.1254 per monthly active user (MAU). Total monthly bill for 100,000 Active Users is $12,537.00.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $7,938.00 per month ($95,256.00/year) on GPT-5.4 nano.
With a direct COGS of $0.1254 per user/month on GPT-5.4 nano, charging at least $0.6269 per user/month ensures an 80%+ software gross margin.