EN ▾

Quickstart: Integrate Uncensored LLM into Your Code

Integrate our uncensored LLM into your video pipeline with this OpenAI-compatible quickstart. Configure your base URL, send your first request, and handle streaming or structured outputs with standard SDKs.

Prerequisites: SDK Installation

Before making requests, ensure your development environment has the appropriate client library installed. We support standard OpenAI-compatible SDKs for Python and Node.js. For Python, install the openai package. For Node.js, use npm install openai. These libraries handle authentication headers, JSON serialization, and streaming events automatically, allowing you to focus on prompt engineering and script generation for your video content.

Configuration: Base URL and Key

Our API uses the standard /v1/chat/completions endpoint but requires a specific base URL to distinguish it from other providers. Set your base_url to https://api.unfilteredvideo.com/v1 and provide the API key generated from your dashboard. No phone number is required for signup, and keys are issued immediately upon account creation. This configuration ensures that your video pipeline tools recognize the uncensored model endpoint correctly.

Sending a Request: Chat Completions

Send a standard chat completion request to generate scripts or captions. Use the model ID uncensored to access our open-weight model tuned for fewer refusals on lawful adult or controversial topics. The following example demonstrates a basic curl request:

curl https://api.unfilteredvideo.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 returns a text response that can be piped directly into your video generation prompt or post-processing script. Ensure your prompt includes context about the video scene to get relevant text output.

Python SDK Integration

For Python projects, initialize the client with your key and the correct base URL. The following snippet shows how to request a script for a video scene:

from openai import OpenAI

client = OpenAI(base_url="https://api.unfilteredvideo.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 approach abstracts the HTTP details, allowing you to parse the response object directly. You can adjust temperature and top_p to control creativity. Remember that the model does not filter lawful adult content, making it suitable for diverse video genres without unexpected refusals.

Node SDK and Streaming

Node.js developers can use the official SDK to handle streaming responses efficiently. This is useful for long scripts where you want to display progress or pipe tokens to a text-to-speech engine in real-time. The following example demonstrates 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 returns tokens incrementally. The final chunk contains usage statistics, including token counts for your billing. This method keeps your application responsive during heavy text generation tasks.

Limits, Errors, and Context Window

Our API has a 100,000 token context window (input + output). There is no separate output cap, and if max_tokens is unset, the response can run to the end of the window. Rate limits are 300 requests per minute and 8 concurrent requests per key. Common errors include 401 (invalid key), 402 (insufficient credit), and 429 (rate limit exceeded). Errors do not consume credit. JSON mode is available via response_format: {"type": "json_object"} for structured data extraction. Use function calling to integrate external tools into your pipeline.

Node.js

import OpenAI from "openai";

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

Capabilities and limits

One table with every limit, feature and price that applies to your key.

ParameterDetails
CompatibilityOpenAI-compatible: any OpenAI SDK or client works — change the base URL and the key
Model IDuncensored
AuthenticationBearer token in the Authorization header
Base URLhttps://api.unfilteredvideo.com/v1
EndpointsPOST /v1/chat/completions · GET /v1/models
Max outputup to the rest of the 100,000-token window; max_tokens optional (no separate cap)
Context window100,000 tokens, input and output combined
JSON moderesponse_format: {"type": "json_object"}
Sampling parameterstemperature, top_p, stop, seed, presence_penalty, frequency_penalty
StreamingYes — server-sent events; the last chunk carries token usage
Function callingYes — tools, tool_choice; replies carry tool_calls, also when streaming; send results back as role: tool
Response headersX-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency
Concurrencyup to 8 in parallel per key
Rate limit300 requests per minute per key
Max bodyup to 8 MB per request
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
Credit expiryno monthly fee; paid credit does not expire
Volume bonus+5% from $50, +10% from $100, +15% from $200
Billingprepaid credit, charged by real token usage; errors and refusals are free
Priceinput $0.15 / 1M tokens, output $0.50 / 1M tokens
Accountsign in with Google or with e-mail + password
Keysone key per account, regenerate any time (the old one stops working)
Contentadult content allowed; sexual content involving minors is refused

HTTP errors

Every error is JSON with a type you can switch on. You are never charged for an error.

StatusTypeReason
400bad_requestmalformed request or too long for the context window
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_blockedsexual content involving minors — refused, not billed
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 this API generate video or audio?

No. This is a text-only chat-completions API. It is optimized for the text-heavy stages of video workflows, such as prompt generation, script writing, and captioning. It does not produce audio, images, or video files.

What is the pricing model?

We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. You preload credit via crypto (USDT on TRC20 or USDC on Base), and errors are free. Credit never expires.

Is the model uncensored?

Yes, the model does not refuse lawful adult, fictional, or controversial topics. However, sexual content involving minors is always blocked. 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.

Get API key