Open account

Uncensored LLM API

AI inference api: uncensored model for developers

Get a single uncensored model for a 100,000 token context window via this OpenAI-compatible API, starting at just $0.15 per million input tokens.

  • POST /v1/chat/completions endpoint
  • Crypto top-ups only
  • No subscription fees

Test with a single call

curl https://api.aiinferenceapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Core capabilities

  1. OpenAI Compatible

    Works with official SDKs by changing base_url and the API key.

  2. No Content Filters

    The model answers without refusals for lawful adult or controversial topics.

  3. 100k Context Window

    Handle long documents with prompt and completion combined up to 100,000 tokens.

  4. Streaming Support

    Receive real-time token usage and content via standard Server-Sent Events.

  5. Function Calling

    Use tools and tool_choice for structured data extraction and automation.

  6. Transparent Pricing

    Pay only for real token usage with prepaid credit that never expires.

Setup process

  1. Sign Up

    Continue with Google or email to get your key instantly.

  2. Top Up

    Add crypto credit to activate your account without a card.

  3. Call API

    Send requests to the endpoint and receive text responses.

Community projects

  1. NSFW Chatbots

    Deploy character-driven bots that handle adult themes without arbitrary blocks.

  2. Creative Writing

    Generate unrestricted fiction with full control over style and tone.

  3. Data Extraction

    Parse complex documents using JSON mode for reliable structured output.

  4. Research Analysis

    Process large datasets within the context window for deep insights.

No Guardrails, No Surprises: The Concrete Differences

We offer a single uncensored LLM without vendor routing or complex tiers. Our API charges strictly per token: $0.15 per million input tokens and $0.50 per million output tokens. You pay only for real usage, not idle capacity. This openai compatible API delivers predictable costs for developers who want direct access to an uncensored model.

Real Math: Your Costs With Our Pricing

Costs scale strictly with token volume, not subscriptions. Input tokens run at $0.15 per million, while output tokens cost $0.50 per million. Errors and refusals consume zero credits. You pay only for what leaves our servers. Prepaid credit never expires. This transparency ensures predictable billing for your uncensored LLM projects without hidden fees.

AI inference API Use Cases for Uncensored Models

The uncensored LLM powers applications requiring unfiltered creative writing, roleplay, and controversial topic analysis without content refusals.

Narrative Generation

Write long-form stories with complex characters and mature themes. The 100,000 token context window preserves narrative continuity across thousands of words without losing track of earlier details.

Roleplay Systems

Build immersive chatbots that stay in character. Users get consistent personality traits without sudden guardrail interruptions during creative scenes.

Research & Analysis

Analyze sensitive political or social topics objectively. The model answers directly without moralizing, providing raw data for your specific use case.

Migrate From OpenAI in Three Lines of Code

Switching to our uncensored LLM requires only three lines of code. You replace the base URL with HTTPS://api.aiinferenceapi.com/v1 and update your API key. Our endpoint supports streaming and JSON mode exactly like OpenAI. You get 100k context windows without vendor lock-in. This works with any standard SDK, letting you deploy immediately. No complex routing or extra configuration is needed for this transition.

From Signup to First Token: How It Works

  1. Visit the Get API key page and sign in with Google or an email password. No phone number required.
  2. Your unique key appears immediately. Copy it to your clipboard.
  3. Update your SDK’s base_url to https://api.aiinferenceapi.com/v1.
  4. Send a request to /v1/chat/completions with model uncensored. The API streams tokens back instantly.

Developers Ask: Real Questions Answered

Yes, you get a direct uncensored LLM without hidden filters.

Our AI inference API is strictly OpenAI-compatible. You only need to change the base URL to HTTPS://api.aiinferenceapi.com/v1 and swap your API key.

Input costs are $0.15 per 1M tokens; output is $0.50 per 1M tokens.

You pay only for real usage.

Frequently asked questions

What is the AI inference API?

It is a hosted, OpenAI-compatible endpoint serving one uncensored model. You send text and receive text. It supports streaming, tools, and JSON mode. The base URL is api.aiinferenceapi.com/v1 for easy integration.

How much does it cost per token?

It charges $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals are free. You pay only for real usage. Credit never expires, so you keep your balance forever.

Can I use it for NSFW content?

Yes. The model answers without refusals for lawful adult topics. It does not filter controversial or sexual themes, except for minors. It is not GPT, Claude, or Gemini. It is a distinct open-weight model.

What is the context window size?

It supports 100,000 tokens total for prompt and completion. You can generate up to 16,000 tokens per request. The default output limit is 2,048 tokens if you do not set max_tokens explicitly in your call.

How do I pay with crypto?

You top up via USDT on TRC20 or USDC on Base. Any whole amount from $20 to $500 works. You receive bonus credit starting at 5% for $50 up to 15% for $200 added instantly.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

Retrieve your API key

Register, retrieve your key, and update the base URL. That is the entire configuration.