v1

latestOpenAPI 3.0.3Apache 2.02026-07-1372170520.1 KB

Inference

Describe a model

Get a description of a model hosted by Pinecone.

You can use hosted models as an integrated part of Pinecone operations or for standalone embedding and reranking. For more details, see Vector embedding and Rerank results.

get/models/{model_name}

Path parameters

model_namestring required

The name of the model to look up.

Headers

X-Pinecone-Api-Versionstring required

Required date-based version header

Response

The model details.

modelstring required

The name of the model.

short_descriptionstring required

A summary of the model.

typestring required

The type of model (e.g. 'embed' or 'rerank').

vector_typestring

Whether the embedding model produces 'dense' or 'sparse' embeddings.

default_dimensioninteger

The default embedding model dimension (applies to dense embedding models only).

modalitystring

The modality of the model (e.g. 'text').

max_sequence_lengthinteger

The maximum tokens per sequence supported by the model.

max_batch_sizeinteger

The maximum batch size (number of sequences) supported by the model.

provider_namestring

The name of the provider of the model.

supported_dimensionsinteger[]

The list of supported dimensions for the model (applies to dense embedding models only).

supported_metricsInferenceModelInfoMetric[]

The distance metrics supported by the model for similarity search.

Example response

{
  "model": "multilingual-e5-large",
  "short_description": "multilingual-e5-large",
  "type": "embed",
  "default_dimension": 1024,
  "modality": "text",
  "max_sequence_length": 512,
  "max_batch_size": 96,
  "provider_name": "NVIDIA",
  "supported_dimensions": [
    1024
  ],
  "supported_parameters": [
    {
      "parameter": "input_type",
      "type": "one_of",
      "value_type": "string",
      "required": true,
      "min": 1,
      "max": 1
    }
  ]
}