---
title: "Create OpenAI-compatible text embeddings via the configured background model"
method: POST
path: "/v1/embeddings"
tags: ["OpenAI Compatible"]
---

# Create OpenAI-compatible text embeddings via the configured background model

`POST /v1/embeddings`

## Request

- Base URL: `https://api.cernion.de`
- URL: `https://api.cernion.de/v1/embeddings`
- Auth: none declared

Inbound OpenAI-compatible facade over the configured Cernion LLM provider (default Gemini). Forwards one or more input strings to the background embedding model and returns vectors in the standard OpenAI embeddings response shape. Only `encoding_format: "float"` is supported.

## Query parameters

- `token` string

## Request body

- object
  - `input` union, required
    - string
    - string[]
  - `model` string
  - `encoding_format` 'float' | 'base64'
  - `token` string: Optional Cernion MCP token for this request. Overrides CERNION_TOKEN when provided.

## Response `200`

OpenAI-compatible embeddings response

- object
  - `object` 'list', required
  - `data` object[], required
    - `object` 'embedding'
    - `index` integer
    - `embedding` number[]
  - `model` string, required
  - `usage` object
  - `cernion` object

---

[API](https://skmtc.dev/cernion/apis/cernion-energy-tools-api.md) · [All operations](https://skmtc.dev/cernion/apis/cernion-energy-tools-api/llms.txt) · [OpenAPI document](https://skmtc.dev/cernion/apis/cernion-energy-tools-api/revisions/cdb94473b538?raw)