# Request schema

> The input object is the spatial equivalent of a prompt.

Source: https://fourechelon.com/docs/request-schema · Machine-readable: https://fourechelon.com/openapi.json · Index: https://fourechelon.com/llms.txt

## Request fields

| Field | Type | Description |
| --- | --- | --- |
| model | string | Model id. Use rowe-1.0. |
| input.task_type | string | fit, stability, placement, embed, understand, reconstruct, predict, act, or optimize. |
| input.cad_scene | object | Native CAD scene with B-rep solids, drawing entities, dimensions, constraints, and optional feature_tree. Preferred for STEP, IGES, DXF, PDF, SVG, and draw.io workflows. |
| input.previous_cad_scene | object | Optional previous native CAD scene for compare and temporal tasks. |
| input.point_cloud_scene | object | Current 3D scene with one or more point cloud groups. |
| input.previous_point_cloud_scene | object | Optional previous scene for temporal prediction. |
| input.image / input.images | object | Optional raster frames, depth maps, or multi-view visual context. |
| input.sensor_readings | object | Optional IMU, GPS, BLE, WiFi, altimeter, or device state readings. |
| input.goal | object | Optional target state for action, routing, placement, or optimization tasks. |
| input.object_id | string | Primary object id used by fit, stability, placement, and tracking tasks. |
| input.secondary_id | string | Target or container object id for fit and placement tasks. |
| input.detail | string | Use compact to reduce structured prediction detail for small or latency-sensitive requests. |