Triss mascottrisscoworker
GitHub ↗
inference costs & methodology

The arithmetic, with the awkward parts left in.

Every number on this page is either a published list price or a measurement from one real week on the Triss codebase. Where Triss does not pay off, that is on the page too.

This estimates API inference costs for the stated workload and pricing assumptions. It does not predict a reduction in a fixed-price Claude or Codex subscription.

The calculator compares an Anthropic list-price baseline (Sonnet/Opus per-token prices) with DeepSeek delegated pricing at the stated cache-hit and workload assumptions — it does not price an arbitrary user-selected provider. Triss is open-source software, not a hosted subscription. Model providers and execution services may charge separately.

Unknown prices stay unknown: usage accounting never treats an unreported price or token count as zero — see the usage accounting methodology.

estimate your own billtoken profile: 28K in / 4.7K out per request
40
65%
Measured week ran at roughly two thirds — bulk reads, reviews, fetches, commit messages.
Primary model
Delegated model class
DeepSeek off-peak: 01:00–04:00 and 06:00–10:00 UTC peak, rest off-peak 50% off — calculator uses off-peak.
77%
average 90–95% now, week 18.5% overall (28.9% on the advanced model)
Agent alone$185
Agent + Triss$75.55
saves $110 / month · 59% less
annual $1,318 saved

Calculator defaults: agent requests per day 40; share delegated to Triss 65%; primary model $3 / $15 per 1M; delegated model class standard (off-peak pricing); cache hit rate 77%.

One measured week — not a projection

209 calls on the Triss codebase itself. A lower-cost model handled bulk reads; a higher-capability model handled reviews. The $2.22 total is the recorded cost of that one usage period — not proof of general savings or quality for every task.

metric
advanced
standard
total
Requests
143
66
209
Input tokens
3.74M
2.10M
5.84M
↳ cache read
1.08M
256
1.08M
↳ cache write
—
—
—
Output tokens
833K
156K
990K
Cost (USD)
$1.88
$0.34
$2.22

Cache read 1.08M — 18.5% of input tokens were cache hits (mostly on the advanced model). Without cache the week would have cost ≈$2.69 instead of $2.22. Cache is the main lever after delegation.

DeepSeek pricing — off-peak USD per 1M (peak 2×) — 2026-08

Source: DeepSeek's official pricing notice and price card; effective 2026-08-16 16:00 UTC. CLI source: src/usage.js DEEPSEEK_PRICING — override via TRISS_PRICE_<MODEL>. Peak: 01:00–04:00/06:00–10:00 UTC; rest off-peak.

metric
standard — $0.22 / $0.007 / $0.66
advanced — $0.66 / $0.022 / $1.98
input uncached / 1M
$0.22
$0.66
cache read / 1M
$0.007
$0.022
output / 1M
$0.66
$1.98

Calculator is honest: providerCost = IN*(1-hit)*inputPrice + IN*hit*cachePrice + OUT*outputPrice — previously cache was ignored and averaged as $0.0052/$0.0131. Cache write for DeepSeek = $0.

Provider avg $0.0106/call measuredDeepSeek standard off-peak $0.22/$0.007/$0.66 per 1M (peak $0.44/$0.014/$1.32)
Tiny lookups

A two-file read roughly breaks even: the round trip plus the summary costs about what doing it directly would.

Judgement calls

Architecture decisions, ambiguous requirements — being wrong is expensive. Cheap models are for volume, not verdicts.