Open account

Chat Completions API Reference

Get your uncensored LLM running with a standard OpenAI-compatible API key. This reference covers authentication, endpoints, streaming, and limits for the most unfiltered AI chat completions.

Authentication & Base URL

Your API key authenticates every request. Use the base URL HTTPS://api.mostunfilteredai.com/v1 with any OpenAI-compatible SDK. The model ID is "uncensored".

curl https://api.mostunfilteredai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize the terms of service in one sentence"}]
  }'

Chat Completions Endpoint

Send POST requests to /v1/chat/completions. This NSFW API endpoint accepts text-in, text-out payloads. No embeddings or image generation here. Just raw LLM output.

Streaming Responses

Use stream=true for real-time token delivery. The final chunk includes usage stats. This keeps your UI responsive during long uncensored AI generation sessions.

stream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Function Calling & Tools

Define tools in your request. The model returns structured tool calls. This enables complex workflows without leaving the API. It handles the logic reliably.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.mostunfilteredai.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

JSON Mode

Set response_format to json_object. The model outputs strict JSON. This is essential for programmatic integration. No markdown wrappers or extra text.

from openai import OpenAI

client = OpenAI(base_url="https://api.mostunfilteredai.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Parameters & Limits

You get 300 requests per minute. Each request supports a 100,000 token context window. Errors are free. Refusals happen only for under-age content. Rate limits trigger 429 errors.

Common questions

What is the context window for most unfiltered AI?

The context window is 100,000 tokens for both prompt and completion. You can output up to 16,000 tokens per request. This allows for deep, extended conversations without losing track.

Why do I get a 402 error?

A 402 error means your prepaid credit is exhausted. Top up via crypto to continue. Errors and refusals do not consume your balance, so you only pay for actual usage.

How many models does this API support?

We serve one uncensored large language model. It is not GPT, Claude, or Grok. It is an open-weight model tuned for adult content without refusals. Use the model ID "uncensored".

Get your API key instantly

Sign up, grab the key, update the base URL. That is all it takes.

Open account