05 /Cost
Cost & latency, estimated before you spend it
Every run is estimated before any expensive stage executes. The acceptance criterion is that this benchmark reports cost/latency without fabricating live numbers — every figure below is either a fixed reference rate or recomputed from the same fixtures.
Fixture mode, no live providers. Every script, storyboard, and asset here is a deterministic, committed fixture — no LLM call, no render worker, no API keys. Assets are synthetic placeholders (CC0, described in
fixtures/assets.json). The interactive pipeline below runs the real engine in your browser, with zero network calls. Runnable harness: benchmarks/vionto.01 /Why zero delta
Estimated vs. observed
Maximum difference between the pre-run cost estimate and the cost recomputed from final artifacts. Zero in fixture mode by construction — there is no live provider to introduce real variance; connecting one is where deviation would first appear.
02 /Per run
Estimate vs. observed, per reference run
| Run | Outcome | Est. tokens | Est. render seconds | Estimated $ | Observed $ | Reference completion |
|---|---|---|---|---|---|---|
Product launch teaser B-01 | Succeeded | 140 | 7.5s | $0.0753 | $0.0753 | 9.1 s |
Birthday memory reel B-02 | Succeeded | 100 | 5.0s | $0.0502 | $0.0502 | 9.1 s |
City timelapse promo B-03 | Succeeded | 100 | 5.0s | $0.0502 | $0.0502 | 9.1 s |
Team standup recap B-04 | Succeeded | 60 | 2.5s | $0.0251 | $0.0251 | 9.1 s |
Quarterly goals announcement B-05 | Cancelled | 60 | 2.5s | $0.0251 | — | — |