---
title: "Generate vectors"
method: POST
path: "/embed"
tags: ["Inference"]
---

# Generate vectors

`POST /embed`

Generate vector embeddings for input data. This endpoint uses Pinecone's [hosted embedding models](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models).

## Headers

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

## Request body

- InferenceEmbedRequest
  - `model` string, required — The [model](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models) to use for embedding generation.
  - `parameters` object — Additional model-specific parameters. Refer to the [model guide](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models) for available model parameters.
  - `inputs` object[], required — List of inputs to generate embeddings for.
    - `text` string — The text input to generate embeddings for.

## Response `200`

OK

- InferenceEmbeddingsList — Embeddings generated for the input.
  - `model` string, required — The model used to generate the embeddings
  - `vector_type` string, required — Indicates whether the response data contains 'dense' or 'sparse' embeddings.
  - `data` InferenceEmbedding[], required — The embeddings generated for the inputs.
    - union — Embedding of a single input
      - object — A dense embedding of a single input
        - `values` number[], required — The dense embedding values.
        - `vector_type` string, required — Indicates whether this is a 'dense' or 'sparse' embedding.
      - object — A sparse embedding of a single input
        - `sparse_values` number[], required — The sparse embedding values.
        - `sparse_indices` integer[], required — The sparse embedding indices.
        - `sparse_tokens` string[] — The normalized tokens used to create the sparse embedding.
        - `vector_type` string, required — Indicates whether this is a 'dense' or 'sparse' embedding.
  - `usage` object, required — Usage statistics for the model inference.
    - `total_tokens` integer — Total number of tokens consumed across all inputs.

## Other responses

- `400` — Bad request. The request body included invalid request parameters.
- `401` — Unauthorized. Possible causes: Invalid API key.
- `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)