What one month of Nova, our internal customer, cost on Fronset
Nova (https://nova.kapualabs.com) is our internal customer: a content and financial-analysis publication run by the team that builds Fronset. Its pipeline has run on Fronset since July. In September it made 198,167 calls across 25 kinds of step, most of them small: extracting claims, identifying languages, summarising, scoring relevance.
Without measurement, a team sends every step like that to one model it trusts. A mid-tier choice would have been Claude Sonnet 5; a cautious one, Claude Opus 5. We priced the month both ways and against what Fronset actually charged:
| Cost | Judged quality | |
|---|---|---|
| Through Fronset, every fee included | $766.79 | 8.45 |
| All on Claude Sonnet 5 | $2,838.43 | 8.52 |
| All on Claude Opus 5 | $6,965.83 | 8.66 |
Quality was not better everywhere: on claim refinement Sonnet 5 beat the models Fronset chose.
The Sonnet 5 and Opus 5 prices are not a simple re-pricing of our tokens. Both models ran on some of these same requests in September, so we used what they really did there: Anthropic counts 48% and 75% more input tokens for the same request, both write longer answers, some of their attempts fail and are still billed, and we applied what we actually pay Anthropic against its list price.
The case page has the method and its limits: Nova, our internal customer: one month on Fronset.