---
title: "Create embeddings"
method: POST
path: "/v1/embeddings"
tags: ["Embeddings"]
---

# Create embeddings

`POST /v1/embeddings`

Convert one or more text inputs into vector embeddings.

## Request body

- Embeddings
  - `model` string, required — Embedding model identifier.
  - `input` union, required — Single input or batch of inputs to embed.
    - string
    - string[]
    - integer[]
    - array[]
      - integer[]
  - `dimensions` integer — Optional target embedding dimension when supported by the model.
  - `encoding_format` 'float' | 'base64' — Return vectors as JSON floats or base64-encoded binary data.

## Response `200`

Successful Response

- EmbeddingsResponse
  - `object` 'list'
  - `model` string, required
  - `data` EmbeddingDataResponse[], required
    - `object` 'embedding'
    - `index` integer, required
    - `embedding` union, required
      - number[]
      - string
  - `usage` EmbeddingUsageResponse, required
    - `prompt_tokens` integer, required
    - `total_tokens` integer, required

## Other responses

- `400` — Bad request
- `401` — Unauthorized
- `402` — Insufficient credits
- `403` — Forbidden
- `410` — Model deprecated
- `422` — Validation error
- `429` — Rate limited
- `500` — Internal server error
- `503` — Upstream service error

---

[API](https://skmtc.net/naga/apis/nagaai-api.md) · [All operations](https://skmtc.net/naga/apis/nagaai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/naga/nagaai-api/revisions/8bfb4677a79e/schema)