Skip to main content
GET
/
v1
/
models
/
{model_id}
/
schema
Get Schema
curl --request GET \
  --url https://api.example.com/v1/models/{model_id}/schema
{
  "feature_names": [
    "<string>"
  ],
  "columns": {},
  "target": {},
  "is_sequence": false,
  "id_column": "<string>",
  "timestamp_column": "<string>"
}

Headers

​
authorization
string | null
​
refresh-token
string | null

Path Parameters

​
model_id
string<uuid>
required

Response

Successful Response

Sidecar at traces/{org}/{model}/schema.json.

Written by api.services.schema_builder.build_schema_manifest after training; read by the inference server when materializing a request DataFrame so categorical codes line up with what the model was trained on. The public HTTP response for GET /schema is served from this type directly — the on-disk sidecar and HTTP shape share one definition because they're identical.

​
feature_names
string[]
required
​
columns
Columns · object
required
​
target
SchemaTarget · object
required
​
is_sequence
boolean
default:false
​
id_column
string | null
​
timestamp_column
string | null