PINECONE_API_KEY="YOUR_API_KEY"
curl "https://api.pinecone.io/models/llama-text-embed-v2" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "X-Pinecone-Api-Version: 2026-04"
{
"model": "llama-text-embed-v2",
"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).",
"type": "embed",
"vector_type": "dense",
"default_dimension": 1024,
"modality": "text",
"max_sequence_length": 2048,
"max_batch_size": 96,
"provider_name": "NVIDIA",
"supported_metrics": [
"Cosine",
"DotProduct"
],
"supported_dimensions": [
384,
512,
768,
1024,
2048
],
"supported_parameters": [
{
"parameter": "input_type",
"required": true,
"type": "one_of",
"value_type": "string",
"allowed_values": [
"query",
"passage"
]
},
{
"parameter": "truncate",
"required": false,
"default": "END",
"type": "one_of",
"value_type": "string",
"allowed_values": [
"END",
"NONE",
"START"
]
},
{
"parameter": "dimension",
"required": false,
"default": 1024,
"type": "one_of",
"value_type": "integer",
"allowed_values": [
384,
512,
768,
1024,
2048
]
}
]
}
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.
PINECONE_API_KEY="YOUR_API_KEY"
curl "https://api.pinecone.io/models/llama-text-embed-v2" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "X-Pinecone-Api-Version: 2026-04"
{
"model": "llama-text-embed-v2",
"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).",
"type": "embed",
"vector_type": "dense",
"default_dimension": 1024,
"modality": "text",
"max_sequence_length": 2048,
"max_batch_size": 96,
"provider_name": "NVIDIA",
"supported_metrics": [
"Cosine",
"DotProduct"
],
"supported_dimensions": [
384,
512,
768,
1024,
2048
],
"supported_parameters": [
{
"parameter": "input_type",
"required": true,
"type": "one_of",
"value_type": "string",
"allowed_values": [
"query",
"passage"
]
},
{
"parameter": "truncate",
"required": false,
"default": "END",
"type": "one_of",
"value_type": "string",
"allowed_values": [
"END",
"NONE",
"START"
]
},
{
"parameter": "dimension",
"required": false,
"default": 1024,
"type": "one_of",
"value_type": "integer",
"allowed_values": [
384,
512,
768,
1024,
2048
]
}
]
}
PINECONE_API_KEY="YOUR_API_KEY"
curl "https://api.pinecone.io/models/llama-text-embed-v2" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "X-Pinecone-Api-Version: 2026-04"
{
"model": "llama-text-embed-v2",
"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).",
"type": "embed",
"vector_type": "dense",
"default_dimension": 1024,
"modality": "text",
"max_sequence_length": 2048,
"max_batch_size": 96,
"provider_name": "NVIDIA",
"supported_metrics": [
"Cosine",
"DotProduct"
],
"supported_dimensions": [
384,
512,
768,
1024,
2048
],
"supported_parameters": [
{
"parameter": "input_type",
"required": true,
"type": "one_of",
"value_type": "string",
"allowed_values": [
"query",
"passage"
]
},
{
"parameter": "truncate",
"required": false,
"default": "END",
"type": "one_of",
"value_type": "string",
"allowed_values": [
"END",
"NONE",
"START"
]
},
{
"parameter": "dimension",
"required": false,
"default": 1024,
"type": "one_of",
"value_type": "integer",
"allowed_values": [
384,
512,
768,
1024,
2048
]
}
]
}
Authorizations
Headers
Required date-based version header
Path Parameters
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.
The name of the model.
"multilingual-e5-large"
A summary of the model.
"multilingual-e5-large"
The type of model (e.g. 'embed' or 'rerank').
"embed"
List of parameters supported by the model.
Show child attributes
Show child attributes
Whether the embedding model produces 'dense' or 'sparse' embeddings.
The default embedding model dimension (applies to dense embedding models only).
1 <= x <= 200001024
The modality of the model (e.g. 'text').
"text"
The maximum tokens per sequence supported by the model.
x >= 1512
The maximum batch size (number of sequences) supported by the model.
x >= 196
The name of the provider of the model.
"NVIDIA"
The list of supported dimensions for the model (applies to dense embedding models only).
1 <= x <= 20000The distance metrics supported by the model for similarity search.
A distance metric that the embedding model supports for similarity searches.
Possible values: cosine, euclidean, or dotproduct.
Was this page helpful?