EN ▾
Get API key
  1. Home
  2. Docs

API Documentation for Uncensored LLM

Get started with the best uncensored llm API in minutes. Use the standard OpenAI-compatible endpoints to send raw text inputs and receive unfiltered model outputs without managing local hardware.

Base URLhttps://api.bestuncensoredllm.com/v1
Modeluncensored

Base URL and Authentication

Our hosted API uses a single base URL for all requests. You authenticate using an API key passed in the Authorization header. Sign up on the Get API key page to receive your key instantly. Each account generates one key, which you can regenerate at any time to revoke access. The model identifier is strictly uncensored, an open-weight model tuned for raw output without content refusals for lawful adult use.

Base URL: https://api.bestuncensoredllm.com/v1. All standard OpenAI SDKs work by pointing to this base URL and providing your key. There is no model routing or choice of vendors; we serve one specific uncensored model.

Privacy note: prompts are not used for training. An account requires only an email and password, with no phone number or credit card needed for the trial tier.

First Request

Send your first request using curl to verify connectivity and receive an uncensored response. The endpoint is POST /v1/chat/completions. Ensure you replace YOUR_API_KEY with your actual key from the dashboard.

This request demonstrates the basic text-in, text-out pipeline. The model will respond based on its training without standard commercial filters, making it ideal for raw data processing or creative writing.

curl https://api.bestuncensoredllm.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."}]
  }'

If you receive a 401 error, your key is invalid or expired. A 402 error indicates insufficient prepaid credit. A 429 error means you have exceeded the rate limit of 300 requests per minute.

Python SDK Integration

Use the official OpenAI Python SDK to interact with the uncensored llm. Install the package via pip, then configure the client to point to our base URL. This approach is preferred for developers building backend services or data processing pipelines.

The SDK handles JSON serialization and streaming automatically. Remember that the model ID is fixed at uncensored. You can pass standard parameters like temperature and max_tokens to control output behavior.

from openai import OpenAI

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

This method is robust for integrating the uncensored ai model for coding tasks or generating large blocks of text. Ensure your code handles potential rate limit errors gracefully by implementing retries.

Node.js SDK Integration

For JavaScript and TypeScript environments, use the OpenAI Node.js SDK. Configure the client with the same base URL and API key as the Python example. This allows you to integrate uncensored responses directly into web applications or Node-based microservices.

The SDK supports the full range of chat completion parameters. Since we do not offer embeddings or image generation, stick to the chat-completions endpoint for all text-based interactions.

import OpenAI from "openai";

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

Use this setup for rapid prototyping of roleplay bots or automated data extraction. The API key is tied to your account, so secure it in your environment variables. Regenerate the key from the dashboard if you suspect a leak.

Streaming Responses

For lower latency experiences, enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) containing partial token outputs. This is essential for real-time chat interfaces where users expect immediate feedback.

Each event contains a chunk of the response. You must parse these events to reconstruct the full message. Streaming does not change the pricing or token counts; you are still charged for the total input and output tokens.

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)

Ensure your client properly handles SSE connections and closes them after the done event. This reduces server load and provides a smoother user experience compared to waiting for the full response.

Models Endpoint, Limits, and Errors

Use GET /v1/models to verify available models. Currently, only uncensored is available. The context window is 100,000 tokens for prompt plus completion. Requests exceeding 8 MB in body size will be rejected.

Rate limits are strict: 300 requests per minute per key. Exceeding this triggers a 429 error. Pricing is usage-based: $0.15 per 1M input tokens and $0.50 per 1M output tokens. Prepaid credit never expires. New accounts get $0.50 trial credit for 7 days. Claim this credit with one click on your API key page. No card is needed for the trial. Sign up now to start testing the best uncensored llm for your projects.

Under the hood: specs

Everything the endpoint can and cannot do, in one place — check it before you top up.

ItemValue
API formatOpenAI-compatible: any OpenAI SDK or client works — change the base URL and the key
Base URLhttps://api.bestuncensoredllm.com/v1
Model IDuncensored
EndpointsPOST /v1/chat/completions · GET /v1/models
API keyBearer token in the Authorization header
Max context100,000 tokens (prompt + completion together)
Max outputup to the rest of the 100,000-token window; max_tokens optional (no separate cap)
Function callingSupported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages
SSE streamingSupported (stream: true), usage included at the end
Structured outputresponse_format: {"type": "json_object"}
Other parameterstemperature, top_p, stop, seed and the two penalties are passed through
Parallel requestsup to 8 in parallel per key
Max body8 MB request body
HeadersX-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency
Rate limit300/min per key
Paymentcrypto: USDT on TRON or USDC on Base, $20–$500, any whole sum
Credit expirypaid credit never expires, no subscription
Free trial$0.50 of credit valid 7 days, no card needed · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up
Price$0.15 per 1M input tokens · $0.50 per 1M output tokens
Bonus credit+5% on $50+, +10% on $100+, +15% on $200+
How you paypay as you go from prepaid credit; nothing is charged for failed or refused requests
Content policyadult content allowed; sexual content involving minors is refused
AccountGoogle or e-mail and password
Key managementone active key per account; a new key replaces the old one

Errors and what to do

Errors come back as JSON with a stable type; failed and refused requests are not billed.

StatusTypeReason
400bad_requestmalformed request or too long for the context window
401missing_key · invalid_key · key_revokedcheck the Authorization header or use your current key
402no_creditout of credit; add credit and retry
403content_blockedsexual content involving minors — refused, not billed
404not_foundunknown endpoint
413request_too_largebody over 8 MB
429rate_limited · concurrencyover 300/min or 8 parallel — back off and retry
503upstream_busymodel busy — retry in a few seconds

Questions and answers

Is there a free uncensored llm option available?

New users get $0.50 of trial credit, one per person, valid for 7 days, requiring only an email and password. This allows you to test the uncensored model without entering payment details. Claim this credit with one click on your API key page. After the trial, you can top up by crypto (USDT on TRC20, USDC on Base) starting from $20.

How does the uncensored llm handle content restrictions?

The model is tuned to answer without refusals for lawful adult, fictional, or controversial topics. However, a hard limit always applies: requests containing sexual content involving minors are blocked. This is the only strict content filter in place.

Can I use multiple API keys for one account?

No, each account is tied to a single API key. You can regenerate the key at any time, which immediately revokes the old one. This ensures simple key management and clear usage tracking per account.

Your key is one form away

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

Get API key