> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pinecone.io/llms.txt
> Use this file to discover all available pages before exploring further.
# 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](https://docs.pinecone.io/guides/index-data/indexing-overview#vector-embedding) and [Rerank results](https://docs.pinecone.io/guides/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
]
}
]
}
```
## OpenAPI
````yaml https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-04/inference_2025-04.oas.yaml get /models/{model_name}
openapi: 3.0.3
info:
title: Pinecone Inference API
description: >-
Pinecone is a vector database that makes it easy to search and retrieve
billions of high-dimensional vectors.
contact:
name: Pinecone Support
url: https://support.pinecone.io
email: support@pinecone.io
license:
name: Apache 2.0
url: https://www.apache.org/licenses/LICENSE-2.0
version: 2025-04
servers:
- url: https://api.pinecone.io
description: Production API endpoints
security:
- ApiKeyAuth: []
tags:
- name: Inference
description: Model inference
externalDocs:
description: More Pinecone.io API docs
url: https://docs.pinecone.io/introduction
paths:
/models/{model_name}:
get:
tags:
- Inference
summary: Describe a model
description: >-
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](https://docs.pinecone.io/guides/index-data/indexing-overview#vector-embedding)
and [Rerank
results](https://docs.pinecone.io/guides/search/rerank-results).
operationId: get_model
parameters:
- in: path
name: model_name
description: The name of the model to look up.
required: true
schema:
type: string
example: multilingual-e5-large
style: simple
responses:
'200':
description: The model details.
content:
application/json:
schema:
$ref: '#/components/schemas/ModelInfo'
examples:
embedding-model:
summary: An embedding model.
value:
max_batch_size: 96
default_dimension: 256
modality: text
model: example-embedding-model
max_sequence_length: 512
provider_name: Embedding Model Provider
supported_dimensions:
- 256
- 512
short_description: An example embedding model.
supported_metrics:
- cosine
- euclidean
supported_parameters:
- allowed_values:
- value1
- value2
parameter: example_required_param
required: true
type: one_of
value_type: string
- allowed_values:
- value1
- value2
default: value1
parameter: example_param_with_default
required: false
type: one_of
value_type: string
- default: 5
max: 10
min: 0
parameter: example_numeric_range
required: false
type: numeric_range
value_type: integer
type: embed
vector_type: dense
rerank-model:
summary: A reranking model.
value:
max_batch_size: 100
modality: text
model: example-reranking-model
max_sequence_length: 1024
provider_name: Reranking Model Provider
short_description: An example reranking model.
supported_parameters:
- default: true
parameter: example_any_value
required: false
type: any
value_type: boolean
type: rerank
'401':
description: 'Unauthorized. Possible causes: Invalid API key.'
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
examples:
unauthorized:
summary: Unauthorized
value:
error:
code: UNAUTHENTICATED
message: Invalid API key.
status: 401
'404':
description: Model not found.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
examples:
model-not-found:
summary: Model not found
value:
error:
code: NOT_FOUND
message: Model example-model not found.
status: 404
'500':
description: Internal server error.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
examples:
internal-server-error:
summary: Internal server error
value:
error:
code: UNKNOWN
message: Internal server error
status: 500
components:
schemas:
ModelInfo:
description: >-
Represents the model configuration including model type, supported
parameters, and other model details.
type: object
properties:
model:
example: multilingual-e5-large
description: The name of the model.
type: string
short_description:
example: multilingual-e5-large
description: A summary of the model.
type: string
type:
example: embed
description: The type of model (e.g. 'embed' or 'rerank').
type: string
vector_type:
description: Whether the embedding model produces 'dense' or 'sparse' embeddings.
type: string
default_dimension:
example: 1024
description: >-
The default embedding model dimension (applies to dense embedding
models only).
type: integer
format: int32
minimum: 1
maximum: 20000
modality:
example: text
description: The modality of the model (e.g. 'text').
type: string
max_sequence_length:
example: 512
description: The maximum tokens per sequence supported by the model.
type: integer
format: int32
minimum: 1
max_batch_size:
example: 96
description: The maximum batch size (number of sequences) supported by the model.
type: integer
format: int32
minimum: 1
provider_name:
example: NVIDIA
description: The name of the provider of the model.
type: string
supported_dimensions:
description: >-
The list of supported dimensions for the model (applies to dense
embedding models only).
type: array
items:
example: 1024
type: integer
format: int32
minimum: 1
maximum: 20000
supported_metrics:
$ref: '#/components/schemas/ModelInfoSupportedMetrics'
supported_parameters:
type: array
items:
$ref: '#/components/schemas/ModelInfoSupportedParameter'
required:
- model
- short_description
- type
- supported_parameters
ErrorResponse:
example:
error:
code: QUOTA_EXCEEDED
message: >-
The index exceeds the project quota of 5 pods by 2 pods. Upgrade
your account or change the project settings to increase the quota.
status: 429
description: The response shape used for all error responses.
type: object
properties:
status:
example: 500
description: The HTTP status code of the error.
type: integer
error:
example:
code: INVALID_ARGUMENT
message: >-
Index name must contain only lowercase alphanumeric characters or
hyphens, and must not begin or end with a hyphen.
description: Detailed information about the error that occurred.
type: object
properties:
code:
type: string
enum:
- OK
- UNKNOWN
- INVALID_ARGUMENT
- DEADLINE_EXCEEDED
- QUOTA_EXCEEDED
- NOT_FOUND
- ALREADY_EXISTS
- PERMISSION_DENIED
- UNAUTHENTICATED
- RESOURCE_EXHAUSTED
- FAILED_PRECONDITION
- ABORTED
- OUT_OF_RANGE
- UNIMPLEMENTED
- INTERNAL
- UNAVAILABLE
- DATA_LOSS
- FORBIDDEN
message:
example: >-
Index name must contain only lowercase alphanumeric characters
or hyphens, and must not begin or end with a hyphen.
type: string
details:
description: >-
Additional information about the error. This field is not
guaranteed to be present.
type: object
required:
- code
- message
required:
- status
- error
ModelInfoSupportedMetrics:
description: The distance metrics supported by the model for similarity search.
type: array
items:
$ref: '#/components/schemas/ModelInfoMetric'
ModelInfoSupportedParameter:
description: >-
Describes a parameter supported by the model, including parameter value
constraints.
type: object
properties:
parameter:
example: input_type
description: The name of the parameter.
type: string
type:
example: one_of
description: >-
The parameter type e.g. 'one_of', 'numeric_range', or 'any'.
If the type is 'one_of', then 'allowed_values' will be set, and the
value specified must be one of the allowed values. 'one_of' is only
compatible with value_type 'string' or 'integer'.
If 'numeric_range', then 'min' and 'max' will be set, then the value
specified must adhere to the value_type and must fall within the
`[min, max]` range (inclusive).
If 'any' then any value is allowed, as long as it adheres to the
value_type.
type: string
value_type:
example: string
description: >-
The type of value the parameter accepts, e.g. 'string', 'integer',
'float', or 'boolean'.
type: string
required:
example: true
description: Whether the parameter is required (true) or optional (false).
type: boolean
allowed_values:
description: The allowed parameter values when the type is 'one_of'.
type: array
items:
anyOf:
- type: string
- type: integer
min:
example: 1
description: >-
The minimum allowed value (inclusive) when the type is
'numeric_range'.
type: number
max:
example: 1
description: >-
The maximum allowed value (inclusive) when the type is
'numeric_range'.
type: number
default:
example: END
description: The default value for the parameter when a parameter is optional.
anyOf:
- type: string
- type: integer
format: int32
- type: number
format: float
- type: boolean
required:
- parameter
- type
- value_type
- required
ModelInfoMetric:
description: >-
A distance metric that the embedding model supports for similarity
searches.
type: string
enum:
- cosine
- euclidean
- dotproduct
securitySchemes:
ApiKeyAuth:
type: apiKey
in: header
name: Api-Key
description: >-
An API Key is required to call Pinecone APIs. Get yours from the
[console](https://app.pinecone.io/).
````