> ## Documentation Index
> Fetch the complete documentation index at: https://docs.refuseless.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> OpenAI-compatible hosted inference for refusal-removed open weights.

# Refuseless API

Refuseless hosts a named lineup of abliterated open-weight models behind an OpenAI-compatible API. If your tooling speaks OpenAI chat completions, it speaks Refuseless — change the base URL, set the model id, use your key.

**Base URL**

```text theme={null}
https://api.refuseless.dev/v1
```

**What you get**

* `POST /v1/chat/completions` — chat completions, streaming + tools
* `POST /v1/completions` — legacy text completions (adapts to chat)
* `GET /v1/models` / `GET /v1/models/{model}` — lineup catalog
* `reasoning_content` passthrough on reasoning models
* Credit-based billing with pre-authorization per request

New here? Start with the [Quickstart](/quickstart).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.