At 40 requests/user/day (totaling 120,000 queries/mo), running AI coding assistant on Fireworks AI — DeepSeek R1 costs $1,317.60 / month ($13.176 / user / mo).
Total expected API invoice for 100 Active Users generating 120,000 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 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Fireworks AI — DeepSeek R1 (Current) | fireworks | $1,317.60 | $13.176 | $15,811.20 | 128,000 |
| GPT-5.6 Terra | openai | $4,204.80 | $42.048 | $50,457.60 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $5,256.00 | $52.56 | $63,072.00 | 256,000 |
| o3-mini | openai | $2,164.80 | $21.648 | $25,977.60 | 200,000 |
| o4-mini | openai | $1,927.20 | $19.272 | $23,126.40 | 256,000 |
| o1-mini | openai | $2,164.80 | $21.648 | $25,977.60 | 128,000 |
At 40 queries per user/day with Fireworks AI — DeepSeek R1, the estimated cost is $13.176 per monthly active user (MAU). Total monthly bill for 100 Active Users is $1,317.60.
Assuming a 60% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Fireworks AI — DeepSeek R1.
With a direct COGS of $13.176 per user/month on Fireworks AI — DeepSeek R1, charging at least $65.88 per user/month ensures an 80%+ software gross margin.