GET
/
models
/
{model_name}
from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")

model = pc.inference.get_model(model_name="llama-text-embed-v2")

print(model)
{'default_dimension': 1024,
 'max_batch_size': 96,
 'max_sequence_length': 2048,
 'modality': 'text',
 'model': 'llama-text-embed-v2',
 'provider_name': 'NVIDIA',
 'short_description': 'A high performance dense embedding model optimized for '
                      'multilingual and cross-lingual text question-answering '
                      'retrieval with support for long documents (up to 2048 '
                      'tokens) and dynamic embedding size (Matryoshka '
                      'Embeddings).',
 'supported_dimensions': [384, 512, 768, 1024, 2048],
 'supported_metrics': [cosine, dotproduct],
 'supported_parameters': [{'allowed_values': ['query', 'passage'],
                           'parameter': 'input_type',
                           'required': True,
                           'type': 'one_of',
                           'value_type': 'string'},
                          {'allowed_values': ['END', 'NONE', 'START'],
                           'default': 'END',
                           'parameter': 'truncate',
                           'required': False,
                           'type': 'one_of',
                           'value_type': 'string'},
                          {'allowed_values': [384, 512, 768, 1024, 2048],
                           'default': 1024,
                           'parameter': 'dimension',
                           'required': False,
                           'type': 'one_of',
                           'value_type': 'integer'}],
 'type': 'embed',
 'vector_type': 'dense'}
from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")

model = pc.inference.get_model(model_name="llama-text-embed-v2")

print(model)
{'default_dimension': 1024,
 'max_batch_size': 96,
 'max_sequence_length': 2048,
 'modality': 'text',
 'model': 'llama-text-embed-v2',
 'provider_name': 'NVIDIA',
 'short_description': 'A high performance dense embedding model optimized for '
                      'multilingual and cross-lingual text question-answering '
                      'retrieval with support for long documents (up to 2048 '
                      'tokens) and dynamic embedding size (Matryoshka '
                      'Embeddings).',
 'supported_dimensions': [384, 512, 768, 1024, 2048],
 'supported_metrics': [cosine, dotproduct],
 'supported_parameters': [{'allowed_values': ['query', 'passage'],
                           'parameter': 'input_type',
                           'required': True,
                           'type': 'one_of',
                           'value_type': 'string'},
                          {'allowed_values': ['END', 'NONE', 'START'],
                           'default': 'END',
                           'parameter': 'truncate',
                           'required': False,
                           'type': 'one_of',
                           'value_type': 'string'},
                          {'allowed_values': [384, 512, 768, 1024, 2048],
                           'default': 1024,
                           'parameter': 'dimension',
                           'required': False,
                           'type': 'one_of',
                           'value_type': 'integer'}],
 'type': 'embed',
 'vector_type': 'dense'}

Authorizations

Api-Key
string
header
required

An API Key is required to call Pinecone APIs. Get yours from the console.

Path Parameters

model_name
string
required

The name of the model to look up.

Response

The model details.

Represents the model configuration including model type, supported parameters, and other model details.

model
string
required

The name of the model.

Example:

"multilingual-e5-large"

short_description
string
required

A summary of the model.

Example:

"multilingual-e5-large"

type
string
required

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

Example:

"embed"

supported_parameters
object[]
required
vector_type
string

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

default_dimension
integer

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

Required range: 1 <= x <= 20000
Example:

1024

modality
string

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

Example:

"text"

max_sequence_length
integer

The maximum tokens per sequence supported by the model.

Required range: x >= 1
Example:

512

max_batch_size
integer

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

Required range: x >= 1
Example:

96

provider_name
string

The name of the provider of the model.

Example:

"NVIDIA"

supported_dimensions
integer[]

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

supported_metrics
enum<string>[]

The distance metrics supported by the model for similarity search.