At 15 requests/user/day (totaling 45,000,000 queries/mo), running Translation on Cerebras — GPT OSS 120B costs $264,375.00 / month ($2.644 / user / mo).
Translation for a 100,000 active users (high-volume consumer / enterprise) audience means 1,500,000 requests per day on average, each carrying 5,000 input and 5,500 output tokens at a 15% cacheable share — so the effective per-request cost on Cerebras — GPT OSS 120B is $0.005875, of which $0.00/mo comes back from prompt caching. Per active user that's $2.644/mo — the number to hold against your pricing tier and gross margin. Charging at least $13.219/user/mo keeps gross margin at or above 80%.
Quick answer
For 100,000 Active Users, Translation on Cerebras — GPT OSS 120B is modeled at 45,000,000 requests per month, costing $264,375.00 per month or $2.644 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 100,000 Active Users generating 45,000,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 15% cache hits on prompt context.
| Model | Provider | Monthly Spend (100,000 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Cerebras — GPT OSS 120B (Current) | cerebras | $264,375.00 | $2.644 | $3,172,500.00 | 128,000 |
| GPT-5.6 Terra | openai | $3,359,250.00 | $33.593 | $40,311,000.00 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $4,199,062.50 | $41.991 | $50,388,750.00 | 256,000 |
| o3-mini | openai | $1,317,937.50 | $13.179 | $15,815,250.00 | 200,000 |
| o4-mini | openai | $1,308,656.25 | $13.087 | $15,703,875.00 | 256,000 |
| o1-mini | openai | $1,317,937.50 | $13.179 | $15,815,250.00 | 128,000 |
At 15 queries per user/day with Cerebras — GPT OSS 120B, the estimated cost is $2.644 per monthly active user (MAU). Total monthly bill for 100,000 Active Users is $264,375.00.
Assuming a 15% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Cerebras — GPT OSS 120B.
With a direct COGS of $2.644 per user/month on Cerebras — GPT OSS 120B, charging at least $13.219 per user/month ensures an 80%+ software gross margin.