EN ▾

Drop-in AI API

Uncensored AI API for Developers

A single, dedicated uncensored LLM API with standard OpenAI compatibility. Change your base URL and key; keep your code.

  • Standard /v1/chat/completions endpoint
  • Uncensored for lawful adult content
  • $0.50 trial, no card required

Get API keyRead the docs

per 1M input tokens
$0.15
Output tokens / 1M
$0.50
token context
100,000
trial credit
$0.50
requests per minute
300
curl https://api.aiapisource.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."}]
  }'

What you get

OpenAI Compatible

Works with official OpenAI SDKs and any compatible client. Only base_url and API key changes are required.

One Uncensored Model

Serves 'uncensored', an open-weight model tuned to answer without content refusals for lawful adult use.

Streaming & Tools

Supports streaming via SSE and tool/function calling. Context window is 100,000 tokens for prompt and completion.

Simple Pricing

$0.15 per 1M input tokens and $0.50 per 1M output tokens. Prepaid credit never expires and no monthly fees.

Privacy First

Prompts are not used for training. Account setup requires only an email and password with no phone number needed.

Strict Limits

300 requests per minute per key and 8 MB request body. No image, audio, or embedding endpoints are offered.

How it works

  1. Sign Up

    Create an account with an email and password to receive your API key immediately.

  2. Configure SDK

    Update your client to use https://api.aiapisource.com/v1 as the base URL and set your new key.

  3. Make Requests

    Send prompts to the /v1/chat/completions endpoint and receive text responses instantly.

What people build with it

Content Generation

Generate creative writing, stories, or scripts without standard model refusals for adult or controversial topics. Ideal for creative projects requiring unrestricted output.

Security Research

Test LLM responses to edge cases or sensitive prompts without hitting hard blocks. Useful for red-teaming or analyzing model behavior on specific inputs.

Chat Applications

Build chat interfaces that prioritize direct answers over conversational filler or safety filters. Works with any OpenAI-compatible chat client.

Data Processing

Extract text or format data from large inputs using the 100k context window. Reliable for batch processing or real-time text transformations.

Drop-in Compatibility

Our API implements the standard OpenAI chat-completions interface. You do not need to install new SDKs or rewrite logic. Simply point your existing client to our base URL and provide your unique API key. The endpoint supports streaming via Server-Sent Events and function calling, matching the behavior developers expect from major providers.

This approach eliminates the complexity of managing multiple vendor integrations. You get a single, dedicated uncensored model without the overhead of gateway routing or abstraction layers. Your code remains portable and simple.

Uncensored Output

The 'uncensored' model is an open-weight large language model hosted on our own GPU servers. It is tuned to answer without content refusals, making it suitable for lawful adult use, fictional writing, and security research. Unlike standard models that may block common topics, this endpoint delivers direct responses.

We maintain one hard content limit that always applies: sexual content involving minors is blocked. Requests containing this specific content will be rejected. For all other lawful uses, the model remains open. It is not GPT, Claude, Gemini, or any other vendor's model; it is a distinct open-weight variant.

Simple Pricing

We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no monthly subscriptions, no tiered pricing, and no hidden fees. You purchase prepaid credit which never expires. Top-ups start at $20 by crypto (USDT on TRC20, USDC on Base).

We also offer bonus credit for larger purchases: +5% bonus when you add $50 or more, +10% bonus for $100 or more, and +15% bonus for $200 or more. New accounts receive $0.50 in trial credit valid for 7 days, requiring no credit card. This transparent model ensures you pay exactly for what you use. Claim this credit with one click on your API key page.

No Vendor Lock-in

Our service is an independent AI API, not a reseller of another company's product. We do not aggregate multiple vendors or route requests between different models. You get one dedicated uncensored model with consistent behavior. This eliminates the risk of sudden pricing changes or model upgrades from third-party providers.

Since we use the standard OpenAI interface, you can switch back to other providers easily if needed. Your code is not tied to our specific implementation details. We do not offer SLA guarantees, SOC2 certifications, or dedicated support channels, keeping our infrastructure lean and cost-effective for developers who prioritize function over enterprise features.

Questions and answers

What is the base URL for the AI API?

The base URL is https://api.aiapisource.com/v1. You can use this with any OpenAI-compatible client or SDK by setting it as the endpoint and providing your API key.

Does the uncensored model support streaming?

Yes, the API supports streaming via Server-Sent Events (SSE). You can also use the /v1/chat/completions endpoint for non-streaming requests and enable function calling for tool use.

What content is blocked?

The only hard limit that always applies is the prohibition of sexual content involving minors. Requests of that kind are blocked. All other lawful adult, fictional, and controversial topics are allowed.

Is there a free trial?

Yes, new users get $0.50 of trial credit valid for 7 days, one per person. Claim this credit with one click on your API key page. No credit card or phone number is required to start. You can top up with as little as $20 to continue using the service.

What is the context window size?

The model supports a 100,000 token context window, which includes both the prompt and the completion. This allows for processing large documents or extensive conversation histories in a single request.

Your key is one form away

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

Get API key