At 4 requests/user/day (totaling 120,000 queries/mo), running Document summarization on Llama 4 Scout (109B MoE) costs $482.40 / month ($0.4824 / user / mo).
Total expected API invoice for 1,000 Active Users generating 120,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 10% cache hits on prompt context.
| Model | Provider | Monthly Spend (1,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Llama 4 Scout (109B MoE) (Current) | meta | $482.40 | $0.4824 | $5,788.80 | 10,000,000 |
| GPT-5.6 Terra | openai | $6,324.00 | $6.324 | $75,888.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $7,905.00 | $7.905 | $94,860.00 | 256,000 |
| o3-mini | openai | $3,451.80 | $3.452 | $41,421.60 | 200,000 |
| o4-mini | openai | $3,369.30 | $3.369 | $40,431.60 | 256,000 |
| o1-mini | openai | $3,451.80 | $3.452 | $41,421.60 | 128,000 |
At 4 queries per user/day with Llama 4 Scout (109B MoE), the estimated cost is $0.4824 per monthly active user (MAU). Total monthly bill for 1,000 Active Users is $482.40.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Llama 4 Scout (109B MoE).
With a direct COGS of $0.4824 per user/month on Llama 4 Scout (109B MoE), charging at least $2.412 per user/month ensures an 80%+ software gross margin.