At 8 requests/user/day (totaling 240,000 queries/mo), running Agentic workflow on Fireworks AI — DeepSeek R1 costs $6,068.40 / month ($6.068 / user / mo).
Total expected API invoice for 1,000 Active Users generating 240,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 65% cache hits on prompt context.
| Model | Provider | Monthly Spend (1,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Fireworks AI — DeepSeek R1 (Current) | fireworks | $6,068.40 | $6.068 | $72,820.80 | 128,000 |
| GPT-5.6 Terra | openai | $12,288.00 | $12.288 | $147,456.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $15,360.00 | $15.36 | $184,320.00 | 256,000 |
| o3-mini | openai | $8,712.00 | $8.712 | $104,544.00 | 200,000 |
| o4-mini | openai | $6,996.00 | $6.996 | $83,952.00 | 256,000 |
| o1-mini | openai | $8,712.00 | $8.712 | $104,544.00 | 128,000 |
At 8 queries per user/day with Fireworks AI — DeepSeek R1, the estimated cost is $6.068 per monthly active user (MAU). Total monthly bill for 1,000 Active Users is $6,068.40.
Assuming a 65% 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 $6.068 per user/month on Fireworks AI — DeepSeek R1, charging at least $30.342 per user/month ensures an 80%+ software gross margin.