At 4 requests/user/day (totaling 600,000 queries/mo), running Document summarization on Llama 3.2 90B Vision costs $13,824.00 / month ($2.765 / user / mo).
Document summarization for a 5,000 active users (growth stage saas) audience means 20,000 requests per day on average, each carrying 25,000 input and 600 output tokens at a 10% cacheable share — so the effective per-request cost on Llama 3.2 90B Vision is $0.023, of which $0.00/mo comes back from prompt caching. Per active user that's $2.765/mo — the number to hold against your pricing tier and gross margin. Charging at least $13.824/user/mo keeps gross margin at or above 80%.
Quick answer
For 5,000 Active Users, Document summarization on Llama 3.2 90B Vision is modeled at 600,000 requests per month, costing $13,824.00 per month or $2.765 per active user.
Method & trust
This projection combines the selected active-user tier, requests per user per day, input/output tokens per request, and the modeled cache share. It is an operating estimate, not a provider invoice; production traffic and retries should be measured against it.
Total expected API invoice for 5,000 Active Users generating 600,000 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 (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Llama 3.2 90B Vision (Current) | meta | $13,824.00 | $2.765 | $165,888.00 | 128,000 |
| GPT-5.6 Sol | openai | $79,050.00 | $15.81 | $948,600.00 | 1,050,000 |
| GPT-5.6 Cyber | openai | $197,625.00 | $39.525 | $2,371,500.00 | 1,050,000 |
| GPT-5.5 Standard | openai | $79,050.00 | $15.81 | $948,600.00 | 512,000 |
| GPT-5.5 Pro | openai | $474,300.00 | $94.86 | $5,691,600.00 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $301,800.00 | $60.36 | $3,621,600.00 | 1,000,000 |
At 4 queries per user/day with Llama 3.2 90B Vision, the estimated cost is $2.765 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $13,824.00.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Llama 3.2 90B Vision.
With a direct COGS of $2.765 per user/month on Llama 3.2 90B Vision, charging at least $13.824 per user/month ensures an 80%+ software gross margin.