At 10 requests/user/day (totaling 1,500,000 queries/mo), running RAG / search-augmented answers on Databricks DBRX Instruct costs $8,550.00 / month ($1.71 / user / mo).
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 |
|---|---|---|---|---|---|
| Databricks DBRX Instruct (Current) | databricks | $8,550.00 | $1.71 | $102,600.00 | 32,768 |
| 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 Databricks DBRX Instruct, the estimated cost is $1.71 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $8,550.00.
Assuming a 50% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Databricks DBRX Instruct.
With a direct COGS of $1.71 per user/month on Databricks DBRX Instruct, charging at least $8.55 per user/month ensures an 80%+ software gross margin.