Filterless ai API Documentation

Base URL and Authentication

The filterless ai API lives at HTTPS://api.filterlessai.com/v1. Pass your API key in the Authorization header. Get a key instantly via Google or email on the dashboard. No phone number required.

One active key per account. Swap it anytime. Prepaid credit never expires. Errors are free.

Use the official OpenAI SDKs by pointing them at this base URL.

First Request

Send a chat completion to the /v1/chat/completions endpoint. Use model uncensored.

Input text. Get text back. No embeddings or images.

Try this:

Copycurl https://api.filterlessai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List three benefits of using Python for data analysis."}]
  }'

Start with model, messages, and max_tokens. Set max_tokens to avoid long waits. Default is 2048 tokens. Max is 16000.

Python SDK Integration

Use the openai Python package. Point it at our base URL. Pass your key.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.filterlessai.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)

Configure the client with base_url and api_key. Send messages. Receive responses. Stream or sync. Choose what fits your app. No extra libraries needed.

Node.js SDK Setup

Install the OpenAI Node package. Initialize with our URL. Set the key.

Copyimport OpenAI from "openai";

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

Call chat.completions.create(). Pass the model name. Get results. Handle errors. Keep it simple. The API works like any OpenAI-compatible service. Just change the URL.

Streaming Responses

Enable streaming by setting stream: true. Receive chunks as they generate. Use Server-Sent Events. Token usage appears in the final chunk. Save bandwidth. Show progress to users. Handle partial text gracefully.

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)

Accumulate tokens. Stop on error. Check the last chunk for usage stats. Keep your UI responsive. Users see text faster. You get real-time data.

Limits, Errors, and Context

Context window is 100,000 tokens. Max output is 16,000 tokens. Request limit: 8 MB body. Rate limit: 300 requests per minute. Concurrency: 8 requests per key.

Errors return standard HTTP codes. 401 means invalid key. 402 means no credit. 429 means rate limit exceeded. Check the response body for details. Fix the key or wait.

Prepaid credit covers usage. Refusals are free. Errors are free. No monthly fee. Credit never expires. Use it when you need it.