At 6 requests/user/day (totaling 450,000 queries/mo), running Customer support chatbot on Text Embedding 004 costs $31.50 / month ($0.0126 / user / mo).
Total expected API invoice for 2,500 Active Users generating 450,000 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 (2,500 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Text Embedding 004 (Current) | $31.50 | $0.0126 | $378.00 | 8,192 | |
| Text Embedding 3 (Small) | openai | $31.50 | $0.0126 | $378.00 | 8,191 |
| Text Embedding 3 (Large) | openai | $204.75 | $0.0819 | $2,457.00 | 8,191 |
At 6 queries per user/day with Text Embedding 004, the estimated cost is $0.0126 per monthly active user (MAU). Total monthly bill for 2,500 Active Users is $31.50.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Text Embedding 004.
With a direct COGS of $0.0126 per user/month on Text Embedding 004, charging at least $0.063 per user/month ensures an 80%+ software gross margin.