At 6 requests/user/day (totaling 180,000 queries/mo), running Customer support chatbot on GPT-4o mini costs $99.225 / month ($0.0992 / user / mo).
Customer support chatbot for a 1,000 active users (seed stage saas) audience means 6,000 requests per day on average, each carrying 3,500 input and 350 output tokens at a 70% cacheable share — so the effective per-request cost on GPT-4o mini is $0.000551, of which $33.075/mo comes back from prompt caching. Per active user that's $0.0992/mo — the number to hold against your pricing tier and gross margin. Charging at least $0.4961/user/mo keeps gross margin at or above 80%.
Quick answer
For 1,000 Active Users, Customer support chatbot on GPT-4o mini is modeled at 180,000 requests per month, costing $99.225 per month or $0.0992 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 1,000 Active Users generating 180,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 70% cache hits on prompt context.
| Model | Provider | Monthly Spend (1,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| GPT-4o mini (Current) | openai | $99.225 | $0.0992 | $1,190.70 | 128,000 |
| GPT-5.6 Luna | openai | $122.22 | $0.1222 | $1,466.64 | 1,050,000 |
| GPT-5.4 mini | openai | $458.325 | $0.4583 | $5,499.90 | 256,000 |
| GPT-5.4 nano | openai | $125.37 | $0.1254 | $1,504.44 | 128,000 |
| Claude Haiku 4.5 | anthropic | $548.10 | $0.5481 | $6,577.20 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $438.48 | $0.4385 | $5,261.76 | 200,000 |
At 6 queries per user/day with GPT-4o mini, the estimated cost is $0.0992 per monthly active user (MAU). Total monthly bill for 1,000 Active Users is $99.225.
Assuming a 70% cache hit rate on repeated system and context tokens, prompt caching saves $33.075 per month ($396.90/year) on GPT-4o mini.
With a direct COGS of $0.0992 per user/month on GPT-4o mini, charging at least $0.4961 per user/month ensures an 80%+ software gross margin.