At 8 requests/user/day (totaling 120,000 queries/mo), running Agentic workflow on OpenRouter Free Tier (Llama 3.3) costs $0.00 / month ($0.00 / user / mo).
Total expected API invoice for 500 Active Users generating 120,000 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 (500 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| OpenRouter Free Tier (Llama 3.3) (Current) | openrouter | $0.00 | $0.00 | $0.00 | 64,000 |
| GPT-5.6 Luna | openai | $614.40 | $1.229 | $7,372.80 | 1,050,000 |
| GPT-5.4 mini | openai | $2,304.00 | $4.608 | $27,648.00 | 256,000 |
| GPT-5.4 nano | openai | $623.40 | $1.247 | $7,480.80 | 128,000 |
| GPT-4o mini | openai | $594.00 | $1.188 | $7,128.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $2,892.00 | $5.784 | $34,704.00 | 1,000,000 |
At 8 queries per user/day with OpenRouter Free Tier (Llama 3.3), the estimated cost is $0.00 per monthly active user (MAU). Total monthly bill for 500 Active Users is $0.00.
Assuming a 65% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on OpenRouter Free Tier (Llama 3.3).
With a direct COGS of $0.00 per user/month on OpenRouter Free Tier (Llama 3.3), charging at least $0.00 per user/month ensures an 80%+ software gross margin.