Quickstart Guide: Uncensored LLM API

Authentication and base URL

Start by generating your key on the dashboard.

Use this base URL for all requests:

HTTPS://api.nsfwia.com/v1

Pass your key in the Authorization header. The endpoint accepts standard OpenAI-compatible clients.

Sending your first request

Send a POST request to /v1/chat/completions to get a response.

Use the model ID "uncensored" for text generation.

Input is text, output is text. No images or video.

Here is a basic curl example:

Copycurl https://api.nsfwia.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the API endpoints and their HTTP methods"}]
  }'

Streaming responses

Enable streaming by setting stream to true.

Receive tokens as they are generated.

Use SSE for real-time output.

This is ideal for roleplay.

Example streaming code:

Copystream = 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 and JSON mode

Use function calling for structured data.

Set response_format to json_object for strict JSON.

Define tools in the request body.

This ensures reliable parsing.

Python SDK example:

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.nsfwia.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: temperature, top_p, and more

Adjust temperature for creativity.

Set top_p for nucleus sampling.

Use stop sequences to end generation.

Seed ensures reproducibility.

Node SDK example:

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.nsfwia.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);

Understanding token costs

Pricing is $0.15 per 1M input tokens and $0.50 per 1M output tokens.

Errors are free. Refusals are free.

Context window is 100,000 tokens total.

Max output is 16,000 tokens per request.

Limits: 300 requests per minute, 8 concurrent requests.

Errors include 401 (invalid key), 402 (no credit), 429 (rate limit).