At 4 requests/user/day (totaling 600,000 queries/mo), running Document summarization on DeepSeek R1 (Reasoner) costs $8,423.40 / month ($1.685 / user / mo).
Total expected API invoice for 5,000 Active Users generating 600,000 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 (5,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| DeepSeek R1 (Reasoner) (Current) | deepseek | $8,423.40 | $1.685 | $101,080.80 | 64,000 |
| GPT-5.6 Terra | openai | $31,620.00 | $6.324 | $379,440.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $39,525.00 | $7.905 | $474,300.00 | 256,000 |
| o3-mini | openai | $17,259.00 | $3.452 | $207,108.00 | 200,000 |
| o4-mini | openai | $16,846.50 | $3.369 | $202,158.00 | 256,000 |
| o1-mini | openai | $17,259.00 | $3.452 | $207,108.00 | 128,000 |
At 4 queries per user/day with DeepSeek R1 (Reasoner), the estimated cost is $1.685 per monthly active user (MAU). Total monthly bill for 5,000 Active Users is $8,423.40.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $615.00 per month ($7,380.00/year) on DeepSeek R1 (Reasoner).
With a direct COGS of $1.685 per user/month on DeepSeek R1 (Reasoner), charging at least $8.423 per user/month ensures an 80%+ software gross margin.