Browse all documentation

SCHEMA

Response schema

Responses include a stable id, typed output array, usage estimates, and a request id. Spatial outputs can include reasoning_scene.v2, a renderable 3D reasoning layer used by Four Cad.

Response fields

Responses include typed outputs, usage metadata, and a request id.

idstring

Unique response id.

objectstring

The object type. Usually response.

modelstring

The model that generated the response.

outputarray

Typed spatial outputs for the requested task. When the request carried a cad_scene, understand, describe, and compare add output[].data.cad_scene: named objects with absolute bounds and parents, connectors with direction, spatial relations, title block, and callout counts; compare adds output[].data.cad_scene_diff (added, removed, moved, re-parented, rewired, dimensions changed).

usageobject

Input spatial tokens, output spatial tokens, projected input cost, projected output cost, and total estimated cost.

request_idstring

Request id for support and debugging.

JSON
{
"id": "resp_4e1f45c7ebd1",
"object": "response",
"model": "rowe-1.0",
"output": [
{
"type": "fit_result",
"data": {
"feasible": false,
"confidence": 0.2862,
"explanation": "Transformer multimodal model predicts fit feasibility=false.",
"reasoning_scene": {
"schema_version": "reasoning_scene.v2",
"scene_id": "four-cad-analysis",
"task_type": "fit",
"objects": [],
"relations": [],
"overlays": [],
"measurements": [],
"reasoning_steps": [],
"suggested_changes": [],
"issue_regions": [],
"fit_results": [],
"comparison_results": [],
"geometry_changes": [],
"text_explanation": "The highlighted geometry shows why the fit check failed."
}
}
}
],
"usage": {
"input_tokens": 42,
"output_tokens": 29,
"estimated_input_cost_usd": 0.000042,
"estimated_output_cost_usd": 0.000116,
"estimated_cost_usd": 0.000158
},
"request_id": "req_..."
}