At 6 requests/user/day (totaling 1,800 queries/mo), running Customer support chatbot on Llama 3.3 70B Instruct costs $1.506 / month ($0.1506 / user / mo).
Customer support chatbot for a 10 active users (alpha / internal testing) audience means 60 requests per day on average, each carrying 3,500 input and 350 output tokens at a 70% cacheable share — so the effective per-request cost on Llama 3.3 70B Instruct is $0.000836, of which $0.00/mo comes back from prompt caching. Per active user that's $0.1506/mo — the number to hold against your pricing tier and gross margin. Charging at least $0.7528/user/mo keeps gross margin at or above 80%.
Quick answer
For 10 Active Users, Customer support chatbot on Llama 3.3 70B Instruct is modeled at 1,800 requests per month, costing $1.506 per month or $0.1506 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 10 Active Users generating 1,800 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 (10 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Llama 3.3 70B Instruct (Current) | meta | $1.506 | $0.1506 | $18.068 | 128,000 |
| GPT-5.6 Terra | openai | $12.222 | $1.222 | $146.664 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $15.278 | $1.528 | $183.33 | 256,000 |
| o3-mini | openai | $7.277 | $0.7277 | $87.318 | 200,000 |
| o4-mini | openai | $6.064 | $0.6064 | $72.765 | 256,000 |
| o1-mini | openai | $7.277 | $0.7277 | $87.318 | 128,000 |
At 6 queries per user/day with Llama 3.3 70B Instruct, the estimated cost is $0.1506 per monthly active user (MAU). Total monthly bill for 10 Active Users is $1.506.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Llama 3.3 70B Instruct.
With a direct COGS of $0.1506 per user/month on Llama 3.3 70B Instruct, charging at least $0.7528 per user/month ensures an 80%+ software gross margin.