Artifact

cost.json makes video API economics visible.

The cost artifact explains processed duration, detector mode, storage, fallback, Ask usage, and retention.

Example shape

{
  "processed_seconds": 20,
  "detector_mode": "cpu_first",
  "fallback_used": false,
  "ask_queries_used": 1,
  "retention_days": 7
}

How to use it

Use cost.json to compare repeated-query workflows, decide retention, and explain why a larger beta plan may be needed.

Review posture

Do not treat an artifact field as a final decision. Pair important artifact claims with evidence references, confidence, detector warnings, and human review boundaries when the workflow is high-risk.

A good product surface links the artifact to the user interface. When a reviewer clicks an event, the UI should show the timestamp, supporting evidence, confidence, and any detector warning. When an answer is generated, the same evidence should be visible. This makes debugging possible and prevents the documentation from becoming a theoretical schema list that developers cannot operationalize.