At 6 requests/user/day (totaling 1,800,000 queries/mo), running Customer support chatbot on Databricks DBRX Instruct costs $4,914.00 / month ($0.4914 / user / mo).
Total expected API invoice for 10,000 Active Users generating 1,800,000 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 (10,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Databricks DBRX Instruct (Current) | databricks | $4,914.00 | $0.4914 | $58,968.00 | 32,768 |
| GPT-5.6 Terra | openai | $12,222.00 | $1.222 | $146,664.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $15,277.50 | $1.528 | $183,330.00 | 256,000 |
| o3-mini | openai | $7,276.50 | $0.7277 | $87,318.00 | 200,000 |
| o4-mini | openai | $6,063.75 | $0.6064 | $72,765.00 | 256,000 |
| o1-mini | openai | $7,276.50 | $0.7277 | $87,318.00 | 128,000 |
At 6 queries per user/day with Databricks DBRX Instruct, the estimated cost is $0.4914 per monthly active user (MAU). Total monthly bill for 10,000 Active Users is $4,914.00.
Assuming a 70% 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 $0.4914 per user/month on Databricks DBRX Instruct, charging at least $2.457 per user/month ensures an 80%+ software gross margin.