At 200 requests/user/day (totaling 600,000,000 queries/mo), running Data extraction & tagging on Databricks DBRX Instruct costs $990,000.00 / month ($9.90 / user / mo).
Total expected API invoice for 100,000 Active Users generating 600,000,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 20% cache hits on prompt context.
| Model | Provider | Monthly Spend (100,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Databricks DBRX Instruct (Current) | databricks | $990,000.00 | $9.90 | $11,880,000.00 | 32,768 |
| GPT-5.6 Terra | openai | $3,768,000.00 | $37.68 | $45,216,000.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $4,710,000.00 | $47.10 | $56,520,000.00 | 256,000 |
| o3-mini | openai | $1,848,000.00 | $18.48 | $22,176,000.00 | 200,000 |
| o4-mini | openai | $1,782,000.00 | $17.82 | $21,384,000.00 | 256,000 |
| o1-mini | openai | $1,848,000.00 | $18.48 | $22,176,000.00 | 128,000 |
At 200 queries per user/day with Databricks DBRX Instruct, the estimated cost is $9.90 per monthly active user (MAU). Total monthly bill for 100,000 Active Users is $990,000.00.
Assuming a 20% 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 $9.90 per user/month on Databricks DBRX Instruct, charging at least $49.50 per user/month ensures an 80%+ software gross margin.