At 8 requests/user/day (totaling 1,200,000 queries/mo), running Agentic workflow on Llama 3.2 3B Instruct costs $1,530.00 / month ($0.306 / user / mo).
Total expected API invoice for 5,000 Active Users generating 1,200,000 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 (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Llama 3.2 3B Instruct (Current) | meta | $1,530.00 | $0.306 | $18,360.00 | 128,000 |
| GPT-5.6 Luna | openai | $6,144.00 | $1.229 | $73,728.00 | 1,050,000 |
| GPT-5.4 mini | openai | $23,040.00 | $4.608 | $276,480.00 | 256,000 |
| GPT-5.4 nano | openai | $6,234.00 | $1.247 | $74,808.00 | 128,000 |
| GPT-4o mini | openai | $5,940.00 | $1.188 | $71,280.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $28,920.00 | $5.784 | $347,040.00 | 1,000,000 |
At 8 queries per user/day with Llama 3.2 3B Instruct, the estimated cost is $0.306 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $1,530.00.
Assuming a 65% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Llama 3.2 3B Instruct.
With a direct COGS of $0.306 per user/month on Llama 3.2 3B Instruct, charging at least $1.53 per user/month ensures an 80%+ software gross margin.