At 10 requests/user/day (totaling 1,500,000 queries/mo), running RAG / search-augmented answers on Gemma 4 31B Instruct costs $3,562.50 / month ($0.7125 / user / mo).
RAG / search-augmented answers for a 5,000 active users (growth stage saas) audience means 50,000 requests per day on average, each carrying 8,000 input and 500 output tokens at a 50% cacheable share — so the effective per-request cost on Gemma 4 31B Instruct is $0.002375, of which $0.00/mo comes back from prompt caching. Per active user that's $0.7125/mo — the number to hold against your pricing tier and gross margin. Charging at least $3.563/user/mo keeps gross margin at or above 80%.
Quick answer
For 5,000 Active Users, RAG / search-augmented answers on Gemma 4 31B Instruct is modeled at 1,500,000 requests per month, costing $3,562.50 per month or $0.7125 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 1,500,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 50% cache hits on prompt context.
| Model | Provider | Monthly Spend (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Gemma 4 31B Instruct (Current) | $3,562.50 | $0.7125 | $42,750.00 | 128,000 | |
| GPT-5.6 Terra | openai | $22,200.00 | $4.44 | $266,400.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $27,750.00 | $5.55 | $333,000.00 | 256,000 |
| o3-mini | openai | $13,200.00 | $2.64 | $158,400.00 | 200,000 |
| o4-mini | openai | $11,550.00 | $2.31 | $138,600.00 | 256,000 |
| o1-mini | openai | $13,200.00 | $2.64 | $158,400.00 | 128,000 |
At 10 queries per user/day with Gemma 4 31B Instruct, the estimated cost is $0.7125 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $3,562.50.
Assuming a 50% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Gemma 4 31B Instruct.
With a direct COGS of $0.7125 per user/month on Gemma 4 31B Instruct, charging at least $3.563 per user/month ensures an 80%+ software gross margin.