At 10 requests/user/day (totaling 30,000 queries/mo), running RAG / search-augmented answers on AI21 Jamba 1.5 Mini costs $54.00 / month ($0.54 / user / mo).
RAG / search-augmented answers for a 100 active users (public launch) audience means 1,000 requests per day on average, each carrying 8,000 input and 500 output tokens at a 50% cacheable share — so the effective per-request cost on AI21 Jamba 1.5 Mini is $0.0018, of which $0.00/mo comes back from prompt caching. Per active user that's $0.54/mo — the number to hold against your pricing tier and gross margin. Charging at least $2.70/user/mo keeps gross margin at or above 80%.
Quick answer
For 100 Active Users, RAG / search-augmented answers on AI21 Jamba 1.5 Mini is modeled at 30,000 requests per month, costing $54.00 per month or $0.54 per active user.
Method & trust
This projection combines the selected active-user tier, requests per user per day, input/output tokens per request, and the modeled cache share. It is an operating estimate, not a provider invoice; production traffic and retries should be measured against it.
Total expected API invoice for 100 Active Users generating 30,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 50% cache hits on prompt context.
| Model | Provider | Monthly Spend (100 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| AI21 Jamba 1.5 Mini (Current) | ai21 | $54.00 | $0.54 | $648.00 | 256,000 |
| GPT-5.6 Luna | openai | $44.40 | $0.444 | $532.80 | 1,050,000 |
| GPT-5.4 mini | openai | $166.50 | $1.665 | $1,998.00 | 256,000 |
| GPT-5.4 nano | openai | $45.15 | $0.4515 | $541.80 | 128,000 |
| GPT-4o mini | openai | $36.00 | $0.36 | $432.00 | 128,000 |
| Claude Haiku 4.5 | anthropic | $207.00 | $2.07 | $2,484.00 | 1,000,000 |
At 10 queries per user/day with AI21 Jamba 1.5 Mini, the estimated cost is $0.54 per monthly active user (MAU). Total monthly bill for 100 Active Users is $54.00.
Assuming a 50% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on AI21 Jamba 1.5 Mini.
With a direct COGS of $0.54 per user/month on AI21 Jamba 1.5 Mini, charging at least $2.70 per user/month ensures an 80%+ software gross margin.