At 4 requests/user/day (totaling 300,000 queries/mo), running Document summarization on Together AI — DeepSeek V4 costs $4,020.00 / month ($1.608 / user / mo).
Total expected API invoice for 2,500 Active Users generating 300,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 10% cache hits on prompt context.
| Model | Provider | Monthly Spend (2,500 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Together AI — DeepSeek V4 (Current) | together | $4,020.00 | $1.608 | $48,240.00 | 1,000,000 |
| GPT-5.6 Terra | openai | $15,810.00 | $6.324 | $189,720.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $19,762.50 | $7.905 | $237,150.00 | 256,000 |
| o3-mini | openai | $8,629.50 | $3.452 | $103,554.00 | 200,000 |
| o4-mini | openai | $8,423.25 | $3.369 | $101,079.00 | 256,000 |
| o1-mini | openai | $8,629.50 | $3.452 | $103,554.00 | 128,000 |
At 4 queries per user/day with Together AI — DeepSeek V4, the estimated cost is $1.608 per monthly active user (MAU). Total monthly bill for 2,500 Active Users is $4,020.00.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Together AI — DeepSeek V4.
With a direct COGS of $1.608 per user/month on Together AI — DeepSeek V4, charging at least $8.04 per user/month ensures an 80%+ software gross margin.