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

# Create embeddings

`POST /llm/v1/embeddings`

Create vector embeddings from text using OpenAI-compatible models. Perfect for semantic search, document similarity, and building RAG systems for legal documents.

## Request body

- object
  - `input` union, required — Text or array of texts to create embeddings for
    - string
    - string[]
  - `model` string, required — Embedding model to use (e.g., text-embedding-ada-002, text-embedding-3-small)
  - `encoding_format` 'float' | 'base64' — Format for returned embeddings
  - `dimensions` integer — Number of dimensions for the embeddings (model-specific)
  - `user` string — Unique identifier for the end-user

## Response `200`

Embeddings created successfully

- object
  - `object` string
  - `data` object[]
    - `object` string
    - `index` integer
    - `embedding` number[]
  - `model` string
  - `usage` object
    - `prompt_tokens` integer
    - `total_tokens` integer

## Other responses

- `400` — Invalid request parameters
- `401` — Invalid API key
- `403` — API key does not have access to LLM service

---

[API](https://skmtc.net/casemark/apis/case-dev-api.md) · [All operations](https://skmtc.net/casemark/apis/case-dev-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/casemark/case-dev-api/revisions/5b7e64e6d6f9/schema)