EN ▾

Uncensored LLM API

Unfiltered Video: The Uncensored LLM API for Video Pipelines

A hosted, OpenAI-compatible chat-completions API delivering raw, uncensored text outputs for video pipeline stages like prompt engineering, script writing, and captioning.

  • No refusals for lawful adult content
  • OpenAI-compatible, 100k context window
  • Crypto payments, pay-per-token

Get API keyRead the docs

Try it in one 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."}]
  }'
per 1M input tokens
$0.15
Output tokens / 1M
$0.50
token context
100,000
trial credit
$0.50
requests per minute
300

What you get

Uncensored Output

The model answers without content refusals for lawful adult, fictional, or controversial topics, giving you full creative control over your video prompts and scripts.

OpenAI Compatible

Integrate using standard SDKs by simply changing the base_url to our endpoint. Works with any client that supports the standard chat-completions format.

Streaming & Tools

Supports Server-Sent Events (SSE) for real-time token streaming, function calling with tools, and strict JSON mode for structured data extraction.

Large Context Window

Handle complex video scripts and long transcripts with a 100,000 token context window, allowing you to process extensive text data in a single request.

Developer First

No subscriptions, no monthly fees. You pay only for real token usage, and errors or refusals are free. Credit never expires.

Instant Access

Get your API key instantly via Google or email. No phone number required, no credit card needed for the trial, and no complex onboarding.

How it works

Create Account

Sign up with Google or email to receive your API key immediately.

Top Up Credit

Add funds via USDT (TRC20) or USDC (Base) starting from $20.

Integrate & Run

Point your OpenAI-compatible client to our base URL and start generating text.

What people build with it

Video Prompt Generation

Generate detailed, uncensored prompts for video generation models without unwanted filtering. Get raw creative variations that adhere to your specific artistic direction.

Script Writing

Produce video scripts that include mature themes, controversial topics, or niche humor without the model refusing to answer. Ideal for adult-oriented or edgy content pipelines.

Captioning & Post-Processing

Extract or rewrite captions from video text data. Use JSON mode to structure extracted data for downstream processing or translation tasks.

Data Extraction

Parse large text documents or transcripts to extract key information. Leverage the large context window to handle long-form content in a single request.

Why Uncensored Text Matters for Video

When building video pipelines, the text stage is often the bottleneck. Standard LLMs refuse to generate content involving adult themes, niche interests, or controversial topics, even when those topics are lawful and relevant to your creative vision. Unfiltered Video provides an uncensored LLM for video prompts that answers directly, giving you full control over your output.

This is critical for prompt engineering. If your video generation model can handle adult content, your prompt generator should not refuse it. Our API serves an open-weight model tuned to answer without content refusals, ensuring your pipeline doesn’t break just because the text contains mature themes. It is not GPT, Claude, or Gemini; it is a dedicated model running on our servers, optimized for raw output.

OpenAI-Compatible Integration

Our API is designed to drop into your existing code with minimal changes. We support the standard OpenAI chat-completions format, meaning you can use the official OpenAI SDKs or any OpenAI-compatible client. You only need to update the base_url to https://api.unfilteredvideo.com/v1 and provide your API key.

The endpoint supports POST /v1/chat/completions for sending requests and GET /v1/models for listing available models. The model id to send is "uncensored". This compatibility ensures you can integrate our text API into your video workflow without rewriting your entire data layer.

Features: Streaming, Tools, and JSON Mode

We provide advanced features necessary for robust pipelines. Streaming via Server-Sent Events (SSE) allows you to receive tokens in real-time, improving the user experience for interactive applications. The last chunk includes token usage details for accurate billing and monitoring.

Function calling (tools) enables your application to interact with external services or structured data. JSON mode ensures the output is strictly formatted as JSON, which is essential for parsing data in automated workflows. You can also control temperature, top_p, stop sequences, and seed for consistent results.

Pricing: Pay Per Token, No Subscriptions

Our pricing is transparent and usage-based. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free, so you only pay for real work. There are no monthly subscriptions or hidden fees. Prepaid credit never expires.

Payments are made via crypto only: USDT (TRC20) or USDC (Base). You can top up any whole amount from $20 to $500. Bonus credit is available for larger top-ups: +5% from $50, +10% from $100, and +15% from $200. We do not accept cards, PayPal, or bank transfers. A new account receives $0.50 of trial credit valid for 7 days, no card needed. Claim this credit with one click on your API key page.

Questions and answers

Is this API good for generating video or images?

No. Unfiltered Video is a text-only chat-completions API. We do not generate audio, images, or video. We provide the text outputs (prompts, scripts, captions) that you can use in your video pipeline. For video generation, you would typically use our text API to generate the prompt, then send that prompt to a dedicated video generation model or API.

What is the context window size?

The context window is 100,000 tokens, which includes both the prompt and the completion. There is no separate output cap, and if you do not set the max_tokens parameter the response can run to the end of the window.

Do you store my prompts for training?

No. Your prompts are not used for training. We only require an email address for your account, and we do not collect phone numbers. Your data remains private and is not used to improve the model.

What content is blocked?

The model does not refuse lawful adult content, but there is one hard content limit that always applies: sexual content involving minors is blocked. Requests containing such content will be refused.

Can I use this for function calling?

Yes. The API supports function calling with tools and tool_choice parameters. You can define functions in your request, and the model will return the appropriate function call in the response. This is useful for automating tasks or interacting with external APIs.

Your key is one form away

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

Get API key