Measured harness ledgerPublic result
DeepSeek V4 ProInfinite cathedral corridor shader — DeepSeek V4 Pro Max
Generate an infinite stained-glass cathedral corridor shader with convincing depth, architectural repetition, light, and motion.
Max reasoningHeadline result
- Workflow cost
- $0.12
- Wall-clock
- 25m 3.25s wall-clock
- Processed tokens
- 3.65M processed
- Record state
- partial_token_timing_artifact_and_local_render_ledger
Public summary
DeepSeek V4 Pro Max partial_token_timing_artifact_and_local_render_ledger ledger: 25m 3.25s wall-clock, 3.65M processed, and $0.12 API-equivalent usage accounting, not an itemized subscription cash charge.
Run identity and stack
- Result ID: infinite-cathedral-shadertoy-deepseek-v4-pro-max
- Technical model: DeepSeek V4 Pro
- Provider: OpenCode Go
- Stack: OpenCode Go
- Stack: Technical model/configuration: DeepSeek V4 Pro
- Stack: ShaderToy fragment shader
- Stack: Harness v1 infinite cathedral prompt
Cost basis
- Visible output and reasoning are both output-priced. OpenCode Go subscription pricing is not divided into a marginal cash cost for this run.
Primary artifact integrity
- Kind: shadertoy-style-fragment-shader
- Path: artifacts/infinite-cathedral-shadertoy-deepseek-v4-pro-max/source/cathedral.glsl
- SHA-256: 27c385c29c290b56257c6aa01abae285e1a4a7e337eefdbc47435b56c1f02f02
Recorded caveats
- Wall-clock is end-to-end workflow latency including tool execution, not model-only compute.
- OpenCode splits one agentic turn into multiple assistant/API messages.
- Cache-read tokens are deeply discounted, so total processed tokens overstate cost.
- The public record excludes private OpenCode session/export data; their source hashes and the stable benchmark-window hash are retained.
- The preview is local model-generated validation evidence, not the required final RTX Pro 6000 capture.
- No initial local FPS, optimized local FPS, RTX Pro 6000 final render, or blind-evaluation record was produced.
Visible evidence gaps
- initial local FPS
- optimized local FPS
- final RTX Pro 6000 1080p60 render or capture metadata
- 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.