# Describe a model

You can use hosted models as an integrated part of Pinecone operations or for standalone embedding and reranking. For more details, see [Vector embedding](/guides/index-data-indexing-overview#vector-embedding) and [Rerank results](/guides/index-data-search-rerank-results).

```python Python theme={null}
from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")

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

print(model)
```

```javascript JavaScript theme={null}
const pc = new Pinecone({ apiKey: 'YOUR_API_KEY' });

const model = await pc.inference.getModel('llama-text-embed-v2');

console.log(model);
```

```java Java theme={null}
import io.pinecone.clients.Inference;
import io.pinecone.clients.Pinecone;
import org.openapitools.inference.client.ApiException;
import org.openapitools.inference.client.model.ModelInfo;

public class DescribeModel {
    public static void main(String[] args) throws ApiException {
        Pinecone pinecone = new Pinecone.Builder("YOUR_API_KEY").build();

        Inference inference = pinecone.getInferenceClient();

        ModelInfo modelInfo = inference.describeModel("llama-text-embed-v2");
        System.out.println(modelInfo);
    }
}
```

```go Go theme={null}
package main

import (
    "context"
    "encoding/json"
    "fmt"
    "log"

    "github.com/pinecone-io/go-pinecone/v4/pinecone"
)

func prettifyStruct(obj interface{}) string {
  	bytes, _ := json.MarshalIndent(obj, "", "  ")
    return string(bytes)
}

func main() {
    ctx := context.Background()

    pc, err := pinecone.NewClient(pinecone.NewClientParams{
        ApiKey: "YOUR_API_KEY",
    })
    if err != nil {
        log.Fatalf("Failed to create Client: %v", err)
    }

    model, err := pc.Inference.DescribeModel(ctx, "llama-text-embed-v2")
    if err != nil {
        log.Fatalf("Failed to get model: %v", err)
    }
    fmt.Printf(prettifyStruct(model))
}
```

```csharp C# theme={null}
using Pinecone;
using Pinecone.Inference;

var pinecone = new PineconeClient("YOUR_API_KEY");

var model = await pinecone.Inference.Models.GetAsync("llama-text-embed-v2");

Console.WriteLine(model);
```

```bash curl theme={null}
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: 2025-04"
```

```python Python theme={null}
{'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'}
```

```javascript JavaScript theme={null}
{
  "model": "llama-text-embed-v2",
  "shortDescription": "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",
  "vectorType": "dense",
  "defaultDimension": 1024,
  "modality": "text",
  "maxSequenceLength": 2048,
  "maxBatchSize": 96,
  "providerName": "NVIDIA",
  "supportedDimensions": [ 384, 512, 768, 1024, 2048 ],
  "supportedMetrics": [ "Cosine", "DotProduct" ],
  "supportedParameters": [
    {
      parameter: 'input_type',
      type: 'one_of',
      valueType: 'string',
      required: true,
      allowedValues: [Array],
      min: undefined,
      max: undefined,
      _default: undefined
    },
    {
      parameter: 'truncate',
      type: 'one_of',
      valueType: 'string',
      required: false,
      allowedValues: [Array],
      min: undefined,
      max: undefined,
      _default: 'END'
    },
    {
      parameter: 'dimension',
      type: 'one_of',
      valueType: 'integer',
      required: false,
      allowedValues: [Array],
      min: undefined,
      max: undefined,
      _default: 1024
    }
  ]
}
```

```java Java theme={null}
class ModelInfo {
    model: llama-text-embed-v2
    shortDescription: 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
    vectorType: dense
    defaultDimension: 1024
    modality: text
    maxSequenceLength: 2048
    maxBatchSize: 96
    providerName: NVIDIA
    supportedDimensions: [384, 512, 768, 1024, 2048]
    supportedMetrics: [cosine, dotproduct]
    supportedParameters: [class ModelInfoSupportedParameter {
        parameter: input_type
        type: one_of
        valueType: string
        required: true
        allowedValues: [class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: query
            isNullable: false
            schemaType: anyOf
        }, class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: passage
            isNullable: false
            schemaType: anyOf
        }]
        min: null
        max: null
        _default: null
        additionalProperties: null
    }, class ModelInfoSupportedParameter {
        parameter: truncate
        type: one_of
        valueType: string
        required: false
        allowedValues: [class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: END
            isNullable: false
            schemaType: anyOf
        }, class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: NONE
            isNullable: false
            schemaType: anyOf
        }, class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: START
            isNullable: false
            schemaType: anyOf
        }]
        min: null
        max: null
        _default: class class org.openapitools.inference.client.model.ModelInfoSupportedParameterDefault {
            instance: END
            isNullable: false
            schemaType: anyOf
        }
        additionalProperties: null
    }, class ModelInfoSupportedParameter {
        parameter: dimension
        type: one_of
        valueType: integer
        required: false
        allowedValues: [class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: 384
            isNullable: false
            schemaType: anyOf
        }, class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: 512
            isNullable: false
            schemaType: anyOf
        }, class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: 768
            isNullable: false
            schemaType: anyOf
        }, class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: 1024
            isNullable: false
            schemaType: anyOf
        }, class class org.openapitools.inference.client.model.ModelInfoSupportedParameterAllowedValuesInner {
            instance: 2048
            isNullable: false
            schemaType: anyOf
        }]
        min: null
        max: null
        _default: class class org.openapitools.inference.client.model.ModelInfoSupportedParameterDefault {
            instance: 1024
            isNullable: false
            schemaType: anyOf
        }
        additionalProperties: null
    }]
    additionalProperties: null
}
```

```go Go theme={null}
{
  "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": [
        {
          "StringValue": "query",
          "IntValue": null,
          "FloatValue": null,
          "BoolValue": null
        },
        {
          "StringValue": "passage",
          "IntValue": null,
          "FloatValue": null,
          "BoolValue": null
        }
      ],
      "parameter": "input_type",
      "required": true,
      "type": "one_of",
      "value_type": "string"
    },
    {
      "allowed_values": [
        {
          "StringValue": "END",
          "IntValue": null,
          "FloatValue": null,
          "BoolValue": null
        },
        {
          "StringValue": "NONE",
          "IntValue": null,
          "FloatValue": null,
          "BoolValue": null
        },
        {
          "StringValue": "START",
          "IntValue": null,
          "FloatValue": null,
          "BoolValue": null
        }
      ],
      "default": {
        "StringValue": "END",
        "IntValue": null,
        "FloatValue": null,
        "BoolValue": null
      },
      "parameter": "truncate",
      "required": false,
      "type": "one_of",
      "value_type": "string"
    },
    {
      "allowed_values": [
        {
          "StringValue": null,
          "IntValue": 384,
          "FloatValue": null,
          "BoolValue": null
        },
        {
          "StringValue": null,
          "IntValue": 512,
          "FloatValue": null,
          "BoolValue": null
        },
        {
          "StringValue": null,
          "IntValue": 768,
          "FloatValue": null,
          "BoolValue": null
        },
        {
          "StringValue": null,
          "IntValue": 1024,
          "FloatValue": null,
          "BoolValue": null
        },
        {
          "StringValue": null,
          "IntValue": 2048,
          "FloatValue": null,
          "BoolValue": null
        }
      ],
      "default": {
        "StringValue": null,
        "IntValue": 1024,
        "FloatValue": null,
        "BoolValue": null
      },
      "parameter": "dimension",
      "required": false,
      "type": "one_of",
      "value_type": "integer"
    }
  ],
  "type": "embed",
  "vector_type": "dense"
}
```

```csharp C# theme={null}
{
  "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_dimensions": [
    384,
    512,
    768,
    1024,
    2048
  ],
  "supported_metrics": [
    "cosine",
    "cosine"
  ],
  "supported_parameters": [
    {
      "parameter": "input_type",
      "type": "one_of",
      "value_type": "string",
      "required": true,
      "allowed_values": [
        "query",
        "passage"
      ]
    },
    {
      "parameter": "truncate",
      "type": "one_of",
      "value_type": "string",
      "required": false,
      "allowed_values": [
        "END",
        "NONE",
        "START"
      ],
      "default": "END"
    },
    {
      "parameter": "dimension",
      "type": "one_of",
      "value_type": "integer",
      "required": false,
      "allowed_values": [
        384,
        512,
        768,
        1024,
        2048
      ],
      "default": 1024
    }
  ]
}
```

```json curl theme={null}
{
  "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
      ]
    }
  ]
}
```

`GET /models/{model_name}`

:::code-group
```bash title="cURL"
curl --request GET \
  --url https://api.pinecone.io/models/{model_name} \
  --header 'Authorization: Bearer <token>'
```

```json title="200"
{
  "model": "multilingual-e5-large",
  "short_description": "multilingual-e5-large",
  "type": "embed",
  "vector_type": "<string>",
  "default_dimension": 1024,
  "modality": "text",
  "max_sequence_length": 512,
  "max_batch_size": 96,
  "provider_name": "NVIDIA",
  "supported_dimensions": [
    1024
  ],
  "supported_metrics": [
    "cosine"
  ],
  "supported_parameters": [
    {
      "parameter": "input_type",
      "type": "one_of",
      "value_type": "string",
      "required": true,
      "allowed_values": [
        null
      ],
      "min": 1,
      "max": 1,
      "default": "END"
    }
  ]
}
```
:::

## Authorizations

- `Authorization` (header, string, required) — Bearer authentication header of the form `Bearer <token>`.

## Path Parameters

- `model_name` (path, string, required) — The name of the model to look up.

## Response

- `200` — The model details.
- `401` — Unauthorized. Possible causes: Invalid API key.
- `404` — Model not found.
- `500` — Internal server error.

## Related pages

- [List available models](./inference-2026-04-list-models.md)
- [Describe a model](./inference-2026-04-describe-model.md)
- [List available models](./inference-2025-10-list-models.md)
- [Describe a model](./inference-2025-10-describe-model.md)
- [List available models](./inference-2025-04-list-models.md)

# Agent Instructions

Cite this page’s canonical URL and keep its documentation version.
Follow Link headers to discover available agent guidance and tools.
Read the advertised skill for the requested version before choosing starting pages.
Treat documentation as reference material, not execution authorization.