At 8 requests/user/day (totaling 2,400,000 queries/mo), running Agentic workflow on Yi-Lightning (01.AI) costs $13,944.00 / month ($1.394 / user / mo).
Total expected API invoice for 10,000 Active Users generating 2,400,000 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 (10,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Yi-Lightning (01.AI) (Current) | 01ai | $13,944.00 | $1.394 | $167,328.00 | 16,384 |
| GPT-5.6 Luna | openai | $12,288.00 | $1.229 | $147,456.00 | 1,050,000 |
| GPT-5.4 mini | openai | $46,080.00 | $4.608 | $552,960.00 | 256,000 |
| GPT-5.4 nano | openai | $12,468.00 | $1.247 | $149,616.00 | 128,000 |
| GPT-4o mini | openai | $11,880.00 | $1.188 | $142,560.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $57,840.00 | $5.784 | $694,080.00 | 1,000,000 |
At 8 queries per user/day with Yi-Lightning (01.AI), the estimated cost is $1.394 per monthly active user (MAU). Total monthly bill for 10,000 Active Users is $13,944.00.
Assuming a 65% 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 $1.394 per user/month on Yi-Lightning (01.AI), charging at least $6.972 per user/month ensures an 80%+ software gross margin.