analyze

Run analysis tools on images or text. Actions include caption, describe_style, detect, embed, prompt_gen, and translate. For local files, upload them first with upload_asset and pass the resulting asset_id. Args: - action: required analysis mode - image: asset_id or URL for image-based actions - text: required for embed and translate, optional for prompt_gen - num_results, model_id, parameters, wait: optional action-specific controls - dry_run: optional — true returns a cost estimate without running or charging credits (sends ?dryRun=true). Applies to all actions. - team_id, project_id: required for OAuth callers Returns: action-specific analysis output. prompt_gen returns prompt suggestions synchronously; the other actions may return immediate results or a polled job result depending on the backend. With dry_run=true the response carries a cost estimate without doing the work. Examples: - "Caption this image" -> action="caption", image="asset_xxx" - "Generate a depth map" -> action="detect", image="asset_xxx", parameters={"modality": "depth"} - "Translate this prompt" -> action="translate", text="..." - "How much would this caption cost?" -> action="caption", image="asset_xxx", dry_run=true Don't use when: You need to generate final user-facing assets. Prefer run_model instead.

{
  "action": "caption",
  "image": "asset_img001",
  "team_id": "team_abc123",
  "project_id": "proj_xyz789"
}

{
  "action": "caption",
  "status": "succeeded",
  "caption": "A majestic dragon with iridescent scales perched on a rocky mountain peak at golden hour, dramatic clouds in the background."
}