At 20 requests/user/day (totaling 60,000 queries/mo), running Content generation on Yi-Lightning (01.AI) costs $16.80 / month ($0.168 / user / mo).
Total expected API invoice for 100 Active Users generating 60,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 30% cache hits on prompt context.
| Model | Provider | Monthly Spend (100 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Yi-Lightning (01.AI) (Current) | 01ai | $16.80 | $0.168 | $201.60 | 16,384 |
| GPT-5.6 Luna | openai | $93.408 | $0.9341 | $1,120.896 | 1,050,000 |
| GPT-5.4 mini | openai | $350.28 | $3.503 | $4,203.36 | 256,000 |
| GPT-5.4 nano | openai | $97.008 | $0.9701 | $1,164.096 | 128,000 |
| GPT-4o mini | openai | $49.32 | $0.4932 | $591.84 | 128,000 |
| Claude Haiku 4.5 | anthropic | $395.04 | $3.95 | $4,740.48 | 1,000,000 |
At 20 queries per user/day with Yi-Lightning (01.AI), the estimated cost is $0.168 per monthly active user (MAU). Total monthly bill for 100 Active Users is $16.80.
Assuming a 30% 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 $0.168 per user/month on Yi-Lightning (01.AI), charging at least $0.84 per user/month ensures an 80%+ software gross margin.