# Serenity Edge API

> Serenity Edge exposes an OpenAI-compatible API for chat completions, embeddings and model discovery, a rerank API, a redaction API for personal data and, in preview, decisions: typed, calibrated answers to typed questions. Requests are authenticated with a bearer API key and served from GPUs in Valencia, Spain. Prompts and completions are never written to disk or logs; prompt prefixes may stay in a volatile memory cache for at most 24 hours.

Source: https://docs.serenityedge.ai/docs/api/edge/serenity-edge-api/

Version: 1.0.0

Serenity Edge exposes an OpenAI-compatible API for chat completions, embeddings and model discovery, a rerank API, a redaction API for personal data and, in preview, decisions: typed, calibrated answers to typed questions. Requests are authenticated with a bearer API key and served from GPUs in Valencia, Spain. Prompts and completions are never written to disk or logs; prompt prefixes may stay in a volatile memory cache for at most 24 hours.

If you already use the OpenAI SDK, point `base_url` to `https://api.serenityedge.ai/v1` and keep the rest of your code.

## Authentication

-   HTTP: Bearer Auth

Send your API key in the `Authorization` header: `Authorization: Bearer <key>`.

<table><tbody><tr><th><p>Security Scheme Type:</p></th><td><p>http</p></td></tr><tr><th><p>HTTP Authorization Scheme:</p></th><td><p>bearer</p></td></tr></tbody></table>

### 

Contact

Serenity Edge:

URL: [https://docs.serenityedge.ai](https://docs.serenityedge.ai/)

### 

Terms of Service

[https://docs.serenityedge.ai/terms/terms-of-service](https://docs.serenityedge.ai/terms/terms-of-service)