At 4 requests/user/day (totaling 6,000 queries/mo), running Document summarization on DeepSeek V3 (Chat) costs $20.118 / month ($0.4024 / user / mo).
Total expected API invoice for 50 Active Users generating 6,000 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 (50 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| DeepSeek V3 (Chat) (Current) | deepseek | $20.118 | $0.4024 | $241.416 | 64,000 |
| GPT-5.6 Luna | openai | $31.62 | $0.6324 | $379.44 | 1,050,000 |
| GPT-5.4 mini | openai | $118.575 | $2.372 | $1,422.90 | 256,000 |
| GPT-5.4 nano | openai | $31.80 | $0.636 | $381.60 | 128,000 |
| GPT-4o mini | openai | $23.535 | $0.4707 | $282.42 | 128,000 |
| Claude Haiku 4.5 | anthropic | $154.50 | $3.09 | $1,854.00 | 1,000,000 |
At 4 queries per user/day with DeepSeek V3 (Chat), the estimated cost is $0.4024 per monthly active user (MAU). Total monthly bill for 50 Active Users is $20.118.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $1.89 per month ($22.68/year) on DeepSeek V3 (Chat).
With a direct COGS of $0.4024 per user/month on DeepSeek V3 (Chat), charging at least $2.012 per user/month ensures an 80%+ software gross margin.