EN ▾
https://api.unrestrictedaiapi.com/v1uncensored2026-10-06
Get API key

Direct LLM Access

Unrestricted AI API for Developers – Start Free

Connect a text model to an application that validates every proposed action. Define tool schemas, check returned arguments, and keep execution permissions in your own code.

  • Own GPU servers, not proxies
  • 100k context window support
  • $0.50 free trial credit

Try it in one request

curl https://api.unrestrictedaiapi.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

Drop this uncensored api into existing OpenAI SDKs by changing the base_url. Supports streaming and function calling out of the box.

Transparent Pay-As-You-Go

paid credit does not expire. No monthly subscriptions or hidden fees. Get bonus credit on top-ups of $50 or more. Trial credit has a separate 7-day validity period.

Validate every response

Use the model within the service’s content rules and handle refusals in your application. Sexual content involving minors is prohibited.

Account key management

Sign up with just an email and password. Your API key appears immediately, ready for your first request.

High Volume Capacity

Handle up to 300 requests per minute with a single key. Regenerate your key anytime to revoke access instantly.

Private & Simple

We do not use your prompts for training. No phone number or credit card is required to start your trial.

How it works

Create Account

Enter your email and password to generate your unique API key instantly.

Add Credits

Load prepaid credits via crypto (USDT or USDC) to start making requests.

Send Requests

Point your client to our base URL and send prompts to the uncensored model.

What people build with it

Uncensored Chatbots

For a chat client, send the relevant messages and specify the expected reply format. Validate the answer before showing it, and keep refusal handling in the application.

Content Generation

Provide a source brief, intended audience and a bounded writing task. Review generated text for unsupported additions before using it in a script or description.

Research & Analysis

Select the relevant passages from a document and ask a bounded question. Compare the answer with the supplied passages; a large context window does not guarantee complete recall or accuracy.

API Development

Use the uncensored llm api as a backend for tools needing unfiltered text processing. Integrate easily with existing OpenAI-compatible workflows.

Uncensored LLM API Overview

This unrestricted ai api exposes one independent text model through Chat Completions. Test saved inputs and validate the returned content before use. A single endpoint does not guarantee identical replies, the absence of refusals or complete privacy.

OpenAI-Compatible Endpoints

Send text to POST /v1/chat/completions and inspect model IDs with GET /v1/models. The base URL is https://api.unrestrictedaiapi.com/v1; set base_url in a compatible client and provide the current key. Test the supported methods and parameters. Image, audio, embedding and fine-tuning endpoints are not provided.

Model Specifications & Context

Requests use model ID uncensored. Input and output together must fit within 100,000 tokens, and the body is limited to 8 MB. Full keys allow 300 requests per minute and 8 concurrent requests; trial keys allow 60 and 2. Keep necessary state in your application and validate each response; context capacity does not guarantee accurate recall.

Pricing & Prepaid Credits

Input costs $0.15 per million tokens and output costs $0.50 per million. Paid top-ups range from $20 to $500 and do not expire. Checkout lists available payment methods. Bonuses are 5% from $50, 10% from $100 and 15% from $200. Eligible accounts can request a $0.50 trial for 7 days, subject to verification and processing.

Questions and answers

Is this API truly uncensored?

The model can be tested with fictional adult-character tasks within the service’s rules. It may still refuse or produce unsuitable content. Review the output before display.

Can I use the OpenAI SDK with this API?

Use the Chat Completions interface at https://api.unrestrictedaiapi.com/v1 with the current key and model uncensored. Test the parameters, streaming and tool-call format your client requires; other OpenAI endpoints are not implied.

How many API keys do I get?

Each account is limited to one API key. You can regenerate the key at any time, which immediately revokes the old one. This keeps your access simple and secure.

Do you use my prompts for training?

No. Your prompts are not used for training our model. We only require an email and password to create your account, keeping the process private and straightforward.

What is the context window size?

The model supports a 100,000 token context window. This allows for long conversations and large document processing within 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

Example: validate a proposed tool call before execution

Define a read-only lookup_item tool accepting an item_id from the test set A12 and B07. Ask the model which item matches a short synthetic request. Parse any returned tool arguments and check the tool name, JSON schema and allowed item IDs before execution. Treat a tool call as a proposal, not permission to perform an action. This example tests application-side validation; your code supplies and executes the tool, not the language model endpoint.