---
title: "Describe a model"
method: GET
path: "/models/{model_name}"
tags: ["Inference"]
---

# Describe a model

`GET /models/{model_name}`

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).

## Path parameters

- `model_name` string, required

## Headers

- `X-Pinecone-Api-Version` string, required

## Response `200`

The model details.

- InferenceModelInfo — Represents the model configuration including model type, supported parameters, and other model details.
  - `model` string, required — The name of the model.
  - `short_description` string, required — A summary of the model.
  - `type` string, required — The type of model (e.g. 'embed' or 'rerank').
  - `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).
  - `modality` string — The modality of the model (e.g. 'text').
  - `max_sequence_length` integer — The maximum tokens per sequence supported by the model.
  - `max_batch_size` integer — The maximum batch size (number of sequences) supported by the model.
  - `provider_name` string — The name of the provider of the model.
  - `supported_dimensions` integer[] — The list of supported dimensions for the model (applies to dense embedding models only).
  - `supported_metrics` InferenceModelInfoMetric[] — The distance metrics supported by the model for similarity search.
  - `supported_parameters` InferenceModelInfoSupportedParameter[], required — List of parameters supported by the model.
    - `parameter` string, required — The name of the parameter.
    - `type` string, required — 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.
    - `value_type` string, required — The type of value the parameter accepts, e.g. 'string', 'integer', 'float', or 'boolean'.
    - `required` boolean, required — Whether the parameter is required (true) or optional (false).
    - `allowed_values` union[] — The allowed parameter values when the type is 'one_of'.
      - union
        - string
        - integer
    - `min` number — The minimum allowed value (inclusive) when the type is 'numeric_range'.
    - `max` number — The maximum allowed value (inclusive) when the type is 'numeric_range'.
    - `default` union — The default value for the parameter when a parameter is optional.
      - string
      - integer
      - number, float
      - boolean

## Other responses

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

---

[API](https://skmtc.net/pinecone/apis/pinecone-api.md) · [All operations](https://skmtc.net/pinecone/apis/pinecone-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/pinecone/pinecone-api/revisions/35876583485d/schema)