EN ▾
Get API key
Uncensored LLM API

Uncensored LLM API for Developers

Drop-in OpenAI compatibility for a single, high-capacity uncensored model. Change your base URL, keep your code.

  • OpenAI compatible API endpoint
  • No subscription or routing fees
  • 100k context window support

Get API keyRead the docs

Try it in one request

curl https://api.llmapisource.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

  1. Drop-in Compatibility

    Use the official OpenAI SDKs with a simple base_url change. No complex routing logic or multi-model aggregation overhead.

  2. Uncensored Generation

    Our open-weight model answers without refusals for lawful adult, fictional, or controversial topics. It is not GPT, Claude, or Gemini.

  3. Transparent Pricing

    Pay-as-you-go prepaid credit starting at $20. No monthly fees, no hidden costs. Credit never expires.

  4. Large Context Window

    Process up to 100,000 tokens in a single request. Ideal for long documents, codebases, or extensive conversation history.

  5. Simple Limits

    300 requests per minute per key. One key per account, easily regenerated. No phone number or card required for trial.

  6. Privacy First

    Prompts are not used for training. Sign up with just an email and password. No vendor lock-in on your data.

How it works

  1. Create Account

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

  2. Add Credit

    Top up by crypto (USDT on TRC20, USDC on Base) to start using the uncensored model.

  3. Integrate Code

    Update your base_url and API key in your existing OpenAI-compatible client.

What people build with it

  1. Creative Writing

    Generate fiction, scripts, or roleplay without content filters blocking mature themes or stylistic choices. Perfect for authors needing unrestricted output.

  2. Security Research

    Analyze models for jailbreaks or generate edge-case prompts without refusal interference. Useful for red-teaming and content analysis.

  3. Data Extraction

    Process large text batches or long documents where context window size matters more than multi-model routing. Get consistent, uncensored results.

  4. Chatbot Development

    Build conversational agents that stay in character without sudden refusals. Ideal for adult-oriented or niche community chatbots.

Drop-in OpenAI Compatibility

Our API implements the standard /v1/chat/completions endpoint. You can use the official OpenAI SDKs for Python, Node.js, and Go by simply changing the base_url and providing your API key. This works with any OpenAI-compatible client, including popular frameworks like LangChain and LlamaIndex. We support streaming via Server-Sent Events (SSE) and tool/function calling. This means you can integrate our uncensored model into your existing infrastructure without rewriting your application logic.

Uncensored Model Performance

We host a single, dedicated open-weight model on our own GPU servers. This model is tuned to answer without content refusals for lawful adult use, fictional scenarios, security research, or controversial topics. It is not GPT, Claude, Gemini, Grok, or any other vendor's model. The model supports a 100,000-token context window, allowing you to process large documents or maintain long conversation histories. Note that we do not offer embeddings, image, audio, or video generation. We focus purely on high-quality text generation.

Developer-First Pricing

We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no subscription fees, no monthly costs, and no model routing fees. You buy prepaid credit starting at $20 via crypto (USDT or USDC). Bonus credit is available for larger top-ups: +5% from $50, +10% from $100, +15% from $200. Paid credit never expires. New users get $0.50 of trial credit, one per person, valid for 7 days, no card needed. This pay-as-you-go model eliminates the overhead of enterprise contracts. Claim this credit with one click on your API key page.

Who This Is Not For

This API is not for you if you need multi-model routing, embeddings, image generation, or fine-tuning. We do not offer SLA guarantees, SOC2 certifications, or on-prem deployment. If you require a specific vendor's model like GPT-4 or Claude, or if you need to aggregate hundreds of models through a gateway, our single-model approach may not fit your architecture. We are an independent service, not a reseller of third-party models. We also block requests involving sexual content with minors, which is a hard limit applied to all requests.

Questions and answers

Is this API compatible with the official OpenAI SDK?

Yes. You can use the standard OpenAI SDKs by changing the base_url to https://api.llmapisource.com/v1 and providing your API key. It supports streaming, tool calling, and standard chat completions.

What is the context window size?

The model supports a 100,000-token context window, covering both the prompt and the completion. This allows for processing large documents or long conversations in a single request.

Do you offer embeddings or image generation?

No. We only offer text-based chat completions via the POST /v1/chat/completions endpoint. We do not support embeddings, image, audio, or video generation, nor do we offer fine-tuning.

How does the pricing work?

You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. You top up with prepaid credit starting at $20. There are no monthly fees, and credit never expires. New accounts get $0.50 in trial credit. Claim this credit with one click on your API key page.

What does 'uncensored' mean for this API?

The model is tuned to answer without refusals for lawful adult, fictional, or controversial topics. It does not apply standard content filters. However, we do block requests involving sexual content with minors, which is a hard limit.

Guides

Practical articles on setup, pricing and integration.

All guides →