At 40 requests/user/day (totaling 60,000 queries/mo), running AI coding assistant on Together AI — GPT-OSS-20B costs $60.00 / month ($1.20 / user / mo).
Total expected API invoice for 50 Active Users generating 60,000 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 (50 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Together AI — GPT-OSS-20B (Current) | together | $60.00 | $1.20 | $720.00 | 32,768 |
| GPT-5.6 Luna | openai | $210.24 | $4.205 | $2,522.88 | 1,050,000 |
| GPT-5.4 mini | openai | $788.40 | $15.768 | $9,460.80 | 256,000 |
| GPT-5.4 nano | openai | $216.24 | $4.325 | $2,594.88 | 128,000 |
| GPT-4o mini | openai | $147.60 | $2.952 | $1,771.20 | 128,000 |
| Claude Haiku 4.5 | anthropic | $931.20 | $18.624 | $11,174.40 | 1,000,000 |
At 40 queries per user/day with Together AI — GPT-OSS-20B, the estimated cost is $1.20 per monthly active user (MAU). Total monthly bill for 50 Active Users is $60.00.
Assuming a 60% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Together AI — GPT-OSS-20B.
With a direct COGS of $1.20 per user/month on Together AI — GPT-OSS-20B, charging at least $6.00 per user/month ensures an 80%+ software gross margin.