Measured harness ledgerPublic result
Kimi K3Interactive Three.js voxel map viewer — Kimi K3 Max
Build a Three.js voxel map viewer with selectable Jungle Temple, Oasis Outpost, and Shrine Village maps, camera reset behavior, and OrbitControls verification.
Max reasoningHeadline result
- Workflow cost
- $1.93
- Wall-clock
- 42:45.7 wall-clock
- Processed tokens
- 2.21M processed
- Record state
- partial_token_timing_and_source_ledger
Public summary
Kimi K3 Max partial_token_timing_and_source_ledger ledger: 42:45.7 wall-clock, 2.21M processed, and $1.93 API-equivalent usage accounting, not an itemized subscription cash charge.
Run identity and stack
- Result ID: interactive-voxel-map-viewer-kimi-k3-max
- Technical model: kimi-k3
- Provider: Kimi Code CLI
- Stack: Kimi Code CLI
- Stack: Technical model/configuration: kimi-k3
- Stack: Three.js voxel viewer
- Stack: OrbitControls
- Stack: Harness v1 voxel-viewer prompt
Cost basis
- The Kimi Code session used an Allegretto subscription. This is token-arithmetic equivalence, not a per-run cash charge.
Primary artifact integrity
- Kind: interactive-threejs-voxel-map-viewer
- Path: artifacts/interactive-voxel-map-viewer-kimi-k3-max/index.html
- SHA-256: eb31672597d803cbf8ff8df297f5855c4868f93a52edaa9c256c39469efbdd63
Recorded caveats
- Wall-clock is end-to-end workflow latency and includes tool execution, browser checks, approvals, and idle time.
- One user prompt produced 26 billable Kimi model requests.
- Kimi Code CLI 0.26.0 exposed no authoritative separate reasoning-token field; output tokens include provider-accounted reasoning, visible prose/code, and tool-call JSON.
- Cache reads are discounted, so total processed tokens overstate cost.
- No /usage screenshot or before-and-after quota record was supplied, so membership quota consumption cannot be measured.
- The static source was archived without a fresh browser run in this environment; no local FPS, browser/hardware environment, final capture, or blind evaluation was supplied.
Visible evidence gaps
- browser and hardware environment
- local FPS measurement receipt
- final capture
- blind-evaluation record
Public result only
This result keeps its public summary and evidence, but it does not currently have a matching Builder test with prompts, projects, Harness workflows or skills.