At 40 requests/user/day (totaling 120,000,000 queries/mo), running AI coding assistant on DeepSeek V4 Flash costs $582,336.00 / month ($5.823 / user / mo).
Total expected API invoice for 100,000 Active Users generating 120,000,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 60% 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 | $582,336.00 | $5.823 | $6,988,032.00 | 1,000,000 |
| GPT-5.6 Luna | openai | $420,480.00 | $4.205 | $5,045,760.00 | 1,050,000 |
| GPT-5.4 mini | openai | $1,576,800.00 | $15.768 | $18,921,600.00 | 256,000 |
| GPT-5.4 nano | openai | $432,480.00 | $4.325 | $5,189,760.00 | 128,000 |
| GPT-4o mini | openai | $295,200.00 | $2.952 | $3,542,400.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $1,862,400.00 | $18.624 | $22,348,800.00 | 1,000,000 |
At 40 queries per user/day with DeepSeek V4 Flash, the estimated cost is $5.823 per monthly active user (MAU). Total monthly bill for 100,000 Active Users is $582,336.00.
Assuming a 60% cache hit rate on repeated system and context tokens, prompt caching saves $368,064.00 per month ($4,416,768.00/year) on DeepSeek V4 Flash.
With a direct COGS of $5.823 per user/month on DeepSeek V4 Flash, charging at least $29.117 per user/month ensures an 80%+ software gross margin.