At 6 requests/user/day (totaling 900,000 queries/mo), running Customer support chatbot on Llama 4 Maverick (400B MoE) costs $1,811.25 / month ($0.3623 / user / mo).
Total expected API invoice for 5,000 Active Users generating 900,000 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 (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Llama 4 Maverick (400B MoE) (Current) | meta | $1,811.25 | $0.3623 | $21,735.00 | 1,000,000 |
| GPT-5.6 Sol | openai | $15,277.50 | $3.056 | $183,330.00 | 1,050,000 |
| GPT-5.6 Cyber | openai | $38,193.75 | $7.639 | $458,325.00 | 1,050,000 |
| GPT-5.5 Standard | openai | $15,277.50 | $3.056 | $183,330.00 | 512,000 |
| GPT-5.5 Pro | openai | $91,665.00 | $18.333 | $1,099,980.00 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $48,510.00 | $9.702 | $582,120.00 | 1,000,000 |
At 6 queries per user/day with Llama 4 Maverick (400B MoE), the estimated cost is $0.3623 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $1,811.25.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Llama 4 Maverick (400B MoE).
With a direct COGS of $0.3623 per user/month on Llama 4 Maverick (400B MoE), charging at least $1.811 per user/month ensures an 80%+ software gross margin.