At 8 requests/user/day (totaling 24,000,000 queries/mo), running Agentic workflow on Microsoft Phi-4 (14B) costs $106,800.00 / month ($1.068 / user / mo).
Total expected API invoice for 100,000 Active Users generating 24,000,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 65% cache hits on prompt context.
| Model | Provider | Monthly Spend (100,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Microsoft Phi-4 (14B) (Current) | microsoft | $106,800.00 | $1.068 | $1,281,600.00 | 16,384 |
| GPT-5.6 Luna | openai | $122,880.00 | $1.229 | $1,474,560.00 | 1,050,000 |
| GPT-5.4 mini | openai | $460,800.00 | $4.608 | $5,529,600.00 | 256,000 |
| GPT-5.4 nano | openai | $124,680.00 | $1.247 | $1,496,160.00 | 128,000 |
| GPT-4o mini | openai | $118,800.00 | $1.188 | $1,425,600.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $578,400.00 | $5.784 | $6,940,800.00 | 1,000,000 |
At 8 queries per user/day with Microsoft Phi-4 (14B), the estimated cost is $1.068 per monthly active user (MAU). Total monthly bill for 100,000 Active Users is $106,800.00.
Assuming a 65% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Microsoft Phi-4 (14B).
With a direct COGS of $1.068 per user/month on Microsoft Phi-4 (14B), charging at least $5.34 per user/month ensures an 80%+ software gross margin.