At 40 requests/user/day (totaling 6,000,000 queries/mo), running AI coding assistant on GPT-5.6 Luna costs $21,024.00 / month ($4.205 / user / mo).
Total expected API invoice for 5,000 Active Users generating 6,000,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 60% cache hits on prompt context.
| Model | Provider | Monthly Spend (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-5.6 Luna (Current) | openai | $21,024.00 | $4.205 | $252,288.00 | 1,050,000 |
| GPT-5.4 mini | openai | $78,840.00 | $15.768 | $946,080.00 | 256,000 |
| GPT-5.4 nano | openai | $21,624.00 | $4.325 | $259,488.00 | 128,000 |
| GPT-4o mini | openai | $14,760.00 | $2.952 | $177,120.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $93,120.00 | $18.624 | $1,117,440.00 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $74,496.00 | $14.899 | $893,952.00 | 200,000 |
At 40 queries per user/day with GPT-5.6 Luna, the estimated cost is $4.205 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $21,024.00.
Assuming a 60% cache hit rate on repeated system and context tokens, prompt caching saves $7,776.00 per month ($93,312.00/year) on GPT-5.6 Luna.
With a direct COGS of $4.205 per user/month on GPT-5.6 Luna, charging at least $21.024 per user/month ensures an 80%+ software gross margin.