ASafarIMShowcase
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

fixture mode has no live variance

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

RunOutcomeEst. tokensEst. render secondsEstimated $Observed $Reference completion
Product launch teaser
B-01
Succeeded1407.5s$0.0753$0.07539.1 s
Birthday memory reel
B-02
Succeeded1005.0s$0.0502$0.05029.1 s
City timelapse promo
B-03
Succeeded1005.0s$0.0502$0.05029.1 s
Team standup recap
B-04
Succeeded602.5s$0.0251$0.02519.1 s
Quarterly goals announcement
B-05
Cancelled602.5s$0.0251