Hanzo
OpenapiMl

Run inference against one of your deployed models

Sends the request body to the named model's predictor and answers the predictor's reply — its status code, its body bytes and its Content-Type, all…

POST /v1/ml/models/{name}/predict

Addresshttps://api.hanzo.ai/v1/ml/models/{name}/predict
MethodPOST
Operationpost_ml_models_by_name_predict
AuthAuthorization: Bearer $HANZO_API_KEY

Sends the request body to the named model's predictor and answers the predictor's reply — its status code, its body bytes and its Content-Type, all unchanged. This is the inference call itself, not a description of one.

VERBATIM IS THE CONTRACT, and it is why this route is not a typed op: a model-side error has to surface as the model's own error, not as this layer's paraphrase of it. The body shape is the kserve v2 inference protocol's, which means the runtime decides it, not this API. The v2 model name defaults to the resource name — kserve's single-model convention — and a multi-model runtime selects one with the model query parameter.

A model that exists but has no serving address yet answers 503 'not ready' rather than a confusing connection error: deployed is not the same as serving. Scoped to the caller's own tenant namespace from the validated org and project, so a name another tenant owns is simply a 404. The predictor's response body is read up to a fixed ceiling.

Request

1 field.

FieldInTypeRequiredDescription
namepathstringyes

Response

The document declares no response body for this operation. It answers 200 on success and the platform error shape on failure — see Errors.

Examples

hanzo ml models predict <name>

ML API · All Hanzo APIs · Interactive reference

How is this guide?

On this page