---
title: "Score similarity between two embedding vectors"
method: POST
path: "/v1/embeddings/similarity"
tags: ["LLM API"]
---

# Score similarity between two embedding vectors

`POST /v1/embeddings/similarity`

## Request

- Base URL: `https://api.algenta.ai`
- URL: `https://api.algenta.ai/v1/embeddings/similarity`
- Auth: one of:
  - HTTP bearer
  - API key in header `X-API-Key`

Runs a deterministic embedding similarity kernel over caller-supplied vectors. This route does not generate embeddings from text; it only scores precomputed embedding vectors with the selected runtime-backed metric.

## Request body

- EmbeddingSimilarityRequest
  - `model` string: Similarity model identifier from GET /v1/models.
  - `left` number[], required: First embedding vector.
  - `right` number[], required: Second embedding vector.

## Response `200`

Successful Response

- EmbeddingSimilarityResponse
  - `object` 'embedding_similarity'
  - `model` string, required
  - `similarity_metric` string, required
  - `score` number, required
  - `dimension` integer, required

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/codna/apis/algenta-api.md) · [All operations](https://skmtc.dev/codna/apis/algenta-api/llms.txt) · [OpenAPI document](https://skmtc.dev/codna/apis/algenta-api/revisions/35d30f84a5df?raw)