At 4 requests/user/day (totaling 12,000,000 queries/mo), running Document summarization on DeepSeek V4 Flash costs $128,724.00 / month ($1.287 / user / mo).
Total expected API invoice for 100,000 Active Users generating 12,000,000 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 (100,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| DeepSeek V4 Flash (Current) | deepseek | $128,724.00 | $1.287 | $1,544,688.00 | 1,000,000 |
| GPT-5.6 Luna | openai | $63,240.00 | $0.6324 | $758,880.00 | 1,050,000 |
| GPT-5.4 mini | openai | $237,150.00 | $2.372 | $2,845,800.00 | 256,000 |
| GPT-5.4 nano | openai | $63,600.00 | $0.636 | $763,200.00 | 128,000 |
| GPT-4o mini | openai | $47,070.00 | $0.4707 | $564,840.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $309,000.00 | $3.09 | $3,708,000.00 | 1,000,000 |
At 4 queries per user/day with DeepSeek V4 Flash, the estimated cost is $1.287 per monthly active user (MAU). Total monthly bill for 100,000 Active Users is $128,724.00.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $12,780.00 per month ($153,360.00/year) on DeepSeek V4 Flash.
With a direct COGS of $1.287 per user/month on DeepSeek V4 Flash, charging at least $6.436 per user/month ensures an 80%+ software gross margin.