At 4 requests/user/day (totaling 6,000 queries/mo), running Document summarization on Perplexity Sonar Deep Research costs $328.80 / month ($6.576 / user / mo).
Document summarization for a 50 active users (private beta) audience means 200 requests per day on average, each carrying 25,000 input and 600 output tokens at a 10% cacheable share — so the effective per-request cost on Perplexity Sonar Deep Research is $0.0548, of which $0.00/mo comes back from prompt caching. Per active user that's $6.576/mo — the number to hold against your pricing tier and gross margin. Charging at least $32.88/user/mo keeps gross margin at or above 80%.
Quick answer
For 50 Active Users, Document summarization on Perplexity Sonar Deep Research is modeled at 6,000 requests per month, costing $328.80 per month or $6.576 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 50 Active Users generating 6,000 queries.
Direct inference cost per MAU to model your SaaS pricing tiers and gross margins.
Savings generated by exploiting 10% cache hits on prompt context.
| Model | Provider | Monthly Spend (50 Active Users) | Cost / User / Mo | Annual Spend | Context Limit |
|---|---|---|---|---|---|
| Perplexity Sonar Deep Research (Current) | perplexity | $328.80 | $6.576 | $3,945.60 | 128,000 |
| GPT-5.6 Sol | openai | $790.50 | $15.81 | $9,486.00 | 1,050,000 |
| GPT-5.6 Cyber | openai | $1,976.25 | $39.525 | $23,715.00 | 1,050,000 |
| GPT-5.5 Standard | openai | $790.50 | $15.81 | $9,486.00 | 512,000 |
| GPT-5.5 Pro | openai | $4,743.00 | $94.86 | $56,916.00 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $3,018.00 | $60.36 | $36,216.00 | 1,000,000 |
At 4 queries per user/day with Perplexity Sonar Deep Research, the estimated cost is $6.576 per monthly active user (MAU). Total monthly bill for 50 Active Users is $328.80.
Assuming a 10% cache hit rate on repeated system and context tokens, prompt caching saves $0.00 per month ($0.00/year) on Perplexity Sonar Deep Research.
With a direct COGS of $6.576 per user/month on Perplexity Sonar Deep Research, charging at least $32.88 per user/month ensures an 80%+ software gross margin.