At 200 requests/user/day (totaling 60,000,000 queries/mo), running Data extraction & tagging on Yi-Lightning (01.AI) costs $18,900.00 / month ($1.89 / user / mo).
Total expected API invoice for 10,000 Active Users generating 60,000,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 20% cache hits on prompt context.
| Model | Provider | Monthly Spend (10,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Yi-Lightning (01.AI) (Current) | 01ai | $18,900.00 | $1.89 | $226,800.00 | 16,384 |
| GPT-5.6 Luna | openai | $37,680.00 | $3.768 | $452,160.00 | 1,050,000 |
| GPT-5.4 mini | openai | $141,300.00 | $14.13 | $1,695,600.00 | 256,000 |
| GPT-5.4 nano | openai | $38,430.00 | $3.843 | $461,160.00 | 128,000 |
| GPT-4o mini | openai | $25,200.00 | $2.52 | $302,400.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $173,400.00 | $17.34 | $2,080,800.00 | 1,000,000 |
At 200 queries per user/day with Yi-Lightning (01.AI), the estimated cost is $1.89 per monthly active user (MAU). Total monthly bill for 10,000 Active Users is $18,900.00.
Assuming a 20% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Yi-Lightning (01.AI).
With a direct COGS of $1.89 per user/month on Yi-Lightning (01.AI), charging at least $9.45 per user/month ensures an 80%+ software gross margin.