EN ▾
Get API key

Raw Text API

Unrestricted AI Models via One OpenAI-Compatible API

Get an uncensored LLM online that removes corporate guardrails without requiring local hardware.

  • 100k context window
  • OpenAI compatible
  • No content filters

Try it in one request

curl https://api.unrestrictedaimodels.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

OpenAI-Compatible Protocol

Use standard OpenAI SDKs by changing base_url. Supports streaming, tool calling, and functions.

Deep Context Handling

Process large documents with a 100,000 token context window for prompt and completion combined.

Direct Model Access

Access a single, powerful uncensored model via the id 'uncensored'. No model routing or selection needed.

Developer-Centric Limits

High throughput with 300 requests per minute per key. Simple 8 MB request body limit.

Flexible Payments

Prepaid credit with no monthly fees. Bonus credits available on top-ups of $50 or more.

Privacy Focused

Prompts are not used for training. Sign up with just an email and password.

How it works

  1. Create Account

    Sign up with email and password to receive your API key instantly.

  2. Add Credit

    Use prepaid credit starting at $20. New accounts get $0.50 free trial credit.

  3. Integrate

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

What people build with it

Creative Writing

Generate raw, unfiltered narratives without style constraints. Ideal for adult themes or controversial topics.

Data Extraction

Parse large documents with deep context. The model focuses on content rather than politeness.

Roleplay Apps

Build characters that stay in persona without breaking for mild profanity or mature themes.

Research Analysis

Get direct answers to security or political questions without corporate bias or hedging.

The Uncensored API

Our unrestricted ai models API provides a hosted, OpenAI-compatible endpoint for developers who want raw text generation. We serve a single large language model tuned to answer without content refusals for lawful adult use. Unlike chat interfaces, we provide the raw text stream and tooling for developers to integrate this unrestricted intelligence directly into their own applications. The model does not refuse controversial, security-research, or mature topics. However, we do maintain one hard content limit: sexual content involving minors is always blocked. This approach ensures you get the freedom of an uncensored ai model while maintaining a baseline of legal safety.

Why Go Uncensored?

Corporate models often filter out useful information to maintain a specific brand voice. They may refuse to discuss sensitive historical events, generate mild profanity, or critique corporate policies. By using an uncensored llm online, you regain control over the output. This is particularly valuable for creative writing, where stylistic constraints can feel artificial, or for data processing where politeness tokens add noise. Our model is an open-weight model run on our own GPU servers, tuned specifically for this purpose. It is not GPT, Claude, Gemini, Grok, DeepSeek, or any other vendor's model. You get a dedicated instance that prioritizes content over conformity.

Developer-First Design

We built this API for engineers who prefer code over UI. The endpoint supports streaming via Server-Sent Events (SSE) and tool/function calling. You can use the official OpenAI SDKs by simply changing the base URL to https://api.unrestrictedaimodels.com/v1. The model ID is 'uncensored'. We do not offer embeddings, image, audio, or video generation, nor do we provide fine-tuning or search capabilities. If you need those features, you will need to combine our text API with other specialized services. Our design is minimal: POST /v1/chat/completions for generation and GET /v1/models for verification. This simplicity reduces integration complexity and debugging time.

Who This Is NOT For

This API is not for users who want a polished, brand-safe chat interface for casual consumers. If you need image generation, voice synthesis, or a turnkey solution with customer support, this is not your product. It is also not ideal for high-volume, low-latency enterprise deployments requiring SLA guarantees, as we do not offer those. If you require multiple model choices or routing between vendors, our single-model approach may be too restrictive. We are an independent service, not a reseller of major cloud providers. We provide the raw intelligence; you handle the application logic and user experience.

Questions and answers

Is this model one of the major vendors like OpenAI or Anthropic?

No. Our model is an open-weight model run on our own servers. It is not GPT, Claude, Gemini, or any other vendor's model. It is tuned specifically for uncensored output.

Do you store or train on my prompts?

No. Your prompts are not used for training. We only require an email and password for your account. We do not collect phone numbers or require credit cards for the trial.

What is the context window size?

The context window is 100,000 tokens, covering both the prompt and the completion. This allows for processing large documents or long conversation histories.

Can I use the OpenAI SDK with this API?

Yes. Our API is fully OpenAI-compatible. You can use standard SDKs by updating the base URL to our endpoint and setting your API key.

Are there any content restrictions?

Yes, one hard limit applies: sexual content involving minors is always blocked. Otherwise, the model does not refuse lawful adult, fictional, or controversial topics.

Your key is one form away

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

Get API key