EN ▾
Get API key

Uncensored Chat Completions API Documentation

This documentation guides you through integrating our uncensored LLM via the standard OpenAI-compatible chat completions endpoint. You can start generating text immediately by configuring your client with our base URL and a freshly generated API key.

On this page
  1. Authentication & Setup
  2. Chat Completions Endpoint
  3. Python SDK Integration
  4. Node.js SDK Integration
  5. Streaming Responses
  6. Rate Limits & Quotas

Authentication & Setup

Access requires a valid API key associated with your account. You generate this key on the Get API Key page after signing up with an email and password. The key is displayed immediately upon creation. To switch from a vendor like OpenAI, update your client configuration to point to our base URL: https://api.unfilteredaimodels.com/v1 and supply your unique API key. We support the standard Authorization header format.

Chat Completions Endpoint

The primary interface is the POST /v1/chat/completions endpoint. It accepts standard message objects and returns text responses. The model ID to specify is uncensored. This endpoint handles raw text generation without the typical corporate guardrails, allowing for adult, controversial, or creative content within legal bounds. You can send your first request using the following example:

curl https://api.unfilteredaimodels.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

This request demonstrates sending a simple system prompt and a user query to generate a response.

Python SDK Integration

Use the official openai Python package. Initialize the client with our base URL and your API key. Then call chat.completions.create with the model ID uncensored. This approach requires zero code changes if you are already using the OpenAI SDK for other services. The following snippet shows how to initialize the client and send a request:

from openai import OpenAI

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

The SDK handles JSON serialization and response parsing automatically.

Node.js SDK Integration

For JavaScript environments, use the openai Node package. Configure the basePath to our endpoint and provide your API key. Call the chat.completions.create method with the uncensored model ID. This ensures compatibility with existing Node.js applications that expect OpenAI-standard responses. Here is how to set up the client:

import OpenAI from "openai";

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

This setup ensures your Node application can communicate with our uncensored model using familiar patterns.

Streaming Responses

Set the stream parameter to true to receive server-sent events (SSE). This allows you to process tokens as they are generated, reducing perceived latency for long responses. The API returns a stream of chunks, each containing partial deltas of the response. Use the following example to implement streaming:

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)

Streaming is ideal for chat interfaces where users expect to see text appearing in real-time.

Rate Limits & Quotas

Your API key is limited to 300 requests per minute. If you exceed this, you receive a 429 Too Many Requests error. You can regenerate your key at any time from your dashboard, which revokes the old key and provides a fresh one with a new rate limit counter. Other errors include 401 for invalid keys and 402 if your prepaid credit is exhausted. The context window supports up to 100,000 tokens for prompt and completion combined. Request bodies are limited to 8 MB.

What the API supports

A quick checklist for developers: format, limits, features, billing.

SpecValue
CompatibilityOpenAI-compatible: any OpenAI SDK or client works — change the base URL and the key
API keyBearer token in the Authorization header
MethodsPOST /v1/chat/completions · GET /v1/models
Base URLhttps://api.unfilteredaimodels.com/v1
Model IDuncensored
Structured outputresponse_format: {"type": "json_object"}
Completion lengthprompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap
Tools / tool callsYes — tools, tool_choice; replies carry tool_calls, also when streaming; send results back as role: tool
StreamingYes — server-sent events; the last chunk carries token usage
Sampling parameterstemperature, top_p, stop, seed and the two penalties are passed through
Context window100,000 tokens (prompt + completion together)
Requests per minute300/min per key
Concurrencyup to 8 in parallel per key
Request sizeup to 8 MB per request
HeadersX-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency
Billingprepaid credit, charged by real token usage; errors and refusals are free
Token pricesinput $0.15 / 1M tokens, output $0.50 / 1M tokens
Free trial$0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up
Paymentcrypto: USDT on TRON or USDC on Base, $20–$500, any whole sum
Subscriptionno monthly fee; paid credit does not expire
Volume bonus+5% from $50, +10% from $100, +15% from $200
Contentuncensored for adults; the only hard rule: no sexual content involving minors
AccountGoogle or e-mail and password
Keysone key per account, regenerate any time (the old one stops working)

Errors and what to do

The type field is stable, the message is for humans. Errors cost nothing.

CodeTypeMeaning
400bad_requestinvalid JSON, empty messages, bad parameter, or a prompt longer than the window — fix and resend
401missing_key · invalid_key · key_revokedno key, wrong key, or a key replaced by a newer one
402no_creditbalance is empty — top up, requests resume at once
403content_blockedrefused by the content policy
404not_foundunknown endpoint
413request_too_largebody over 8 MB
429rate_limited · concurrencyslow down: rate or parallel limit reached
503upstream_busymodel busy — retry in a few seconds

Questions and answers

Does regenerating my API key reset my rate limit?

Yes. Regenerating your key revokes the old one and issues a new one with a fresh rate limit counter. The 300 requests per minute limit applies to the specific key in use.

What content is restricted?

The model does not refuse most adult, fictional, or controversial topics. However, a hard limit always applies: sexual content involving minors is blocked.

Is the model fine-tuned or a standard GPT?

It is an open-weight model run on our own GPU servers, tuned for uncensored output. It is not GPT, Claude, or any other vendor's model.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.