AI Model Reviewer

Kimi K3 in OpenCode 1.18.32

skills off

← Open in the gallerySame prompt, all models

Poster frame of Kimi K3's page
Open the original page

The model's own page, run in a sandboxed frame only when you ask (a page that needs its own origin opens in a new tab on a separate demo site). Phones get a full-screen player capped at 1.5x pixel density (2x on larger screens) so it stays smooth; the original page runs uncapped. It starts in its auto-tour (T switches to play mode on a keyboard).

Stopped by usFolding roadmax effortNeutral harness

Wall time 44m 37sCost $1.89 reported

Snapshot 1 of 1 saved during Kimi K3's run
Still snapshots saved during the run (no motion recording): 1 distinct frame.

Review

No verdict yet.

The full review

Stopped by us. Stopped by us (codespaces lane core-hour budget (60) reached; stopped by the lane, artifacts kept); not a model failure.

Scores

Not scored: only runs that finished on their own are scored.

Downloads

Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.

The exact prompt

as run, 721 characters. Every result for this prompt

ok here it is - my first Opus 5.5 vibecoded threejs 3D experience

my God!! Opus is creative!!

I made a road that forgets which way is down.

It folds 90° up a yellow wall, runs upside down across a ceiling, and turns into sheet music: steer through the notes to play each street's melody.

Watercolour. Ink. A radio on the roof.

#vibejam Build it as index.html (plus any local asset files you create) in the current directory. Three.js may load from a pinned CDN. You may serve it locally and open it in headless chromium (/usr/bin/chromium, software WebGL, no GPU) to screenshot and inspect your own output, and iterate on your own before finishing. Close any browser you open as soon as you've taken your screenshot.

How it was made

Wall time 44m 37sFirst artifact at 23m 32s10 saved versions

Versions saved during the run

10 intermediate outputs, in the order the model wrote them.

Step by step

The prompt, every agent turn and tool call (tool name and a one-line summary; inputs and outputs are not shown), then the final message. The full machine-format transcript is published as a scrubbed download.

Show all 102 steps

Loading the timeline…

Download the full transcript OpenCode session export, 353 KB. Scrubbed: anything that looks like a key, token, e-mail address or phone number is replaced, and account details and the test machine's file paths are removed.

Cost breakdown

Headline cost $1.89, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $1.89.

Tokens by typeTokens$ per 1MCost
Input (uncached)95,927$3.00$0.2878
Cache write0$3.00$0
Cache read2,159,957$0.30$0.6480
Output63,549$15.00$0.9532
of which reasoning40,707billed as output
Total computed from tokens
$1.8890
Total reported by the harness
$1.8890
Difference
matches

OpenCode 1.18.32 reported its own total; token counts x list prices shown beside it. The harness reports reasoning tokens separately from output; here output includes them (22,842 visible + 40,707 reasoning), and both bill at the output rate.

Prices: https://platform.kimi.ai/docs/pricing/chat, 2026-09-24.

Run notes

one prompt, agentic harness (self-review allowed)reconstructed promptlabelled re-run (of folding_road_threejs__opencode__kimi-k3)

  • frozen prompt (reconstructed): recovery/prompts_recovered/folding_road_threejs.assembled_candidate.txt: verbatim ask + recorded harness suffix
  • plain OpenCode config copy (providers only; no ECC instructions/agents)
  • opencode export written to a file (not piped)
  • Run on a GitHub Codespace (codespaces lane of box-fleet); model calls reached the providers through a credential relay on the home machine (no keys in the codespace).
  • Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
  • Isolation audit: outside paths seen