Developer-First Uncensored API

Unrestricted gpt Alternative API

Get an uncensored model with a 100k context window, paying only for tokens used. No monthly fees, no content blocks, and transparent prepaid billing for reliable unrestricted AI generation.

100,000 token context window
Zero monthly subscription fees
Crypto-only USDT or USDC top-ups

Open account View documentation

curl https://api.gptunrestricted.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a list of top ten coffee shops near me"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.gptunrestricted.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.gptunrestricted.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

per 1M input tokens: $0.15
Output tokens / 1M: $0.50
token context: 100,000
trial credit: $0.50
requests per minute: 300

Core features

OpenAI-Compatible Endpoints

Drop-in replacement for existing clients using standard /v1/chat/completions.

Massive Context Window

Process up to 100k tokens for long-form generation needs.

Transparent Token Billing

Pay $0.15 per million input tokens and $0.50 for output.

Crypto Top-Ups Only

Fund your account using USDT on TRC20 or USDC on Base.

Streaming & JSON Mode

Support for SSE streaming and strict JSON response formatting.

Instant Account Creation

Setup process

Create Your Account

Top Up With Crypto

Add USDT or USDC to your prepaid balance with no card needed.

Update Base URL

Point your SDK to our API endpoint and start sending requests.

Use cases

Long-Form Storytelling

Generate complete novels without losing context due to short window limits.

Uncensored Roleplay

Run adult or unrestricted fictional narratives without unexpected content refusals.

Data Analysis

Process large documents by leveraging the 100k token context window.

Developer Prototyping

Test chat completions with a reliable uncensored LLM backend.

How this uncensored model differs from typical alternatives

We run our own tuned model, not a proxy for another vendor. Our API serves a single uncensored large language model with a 100k context window. You get consistent, non-filtered responses without the guardrails of major providers. We do not route traffic or resell other models.

Why 'unrestricted GPT' matters for your content workflow

Our uncensored LLM removes content filters so your creative workflow stays uninterrupted.

Explicit Roleplay

Generate mature fictional stories without sudden refusals or generic safety blocks blocking your narrative flow.

Long Context

Leverage the 100k token window for deep memory in complex, multi-turn creative sessions.

Cost Control

Pay only for tokens used with prepaid crypto credit; no surprise monthly subscription fees.

Three steps to migrate from your current provider

Update your base URL and API key to switch instantly.

Change the base URL to HTTPS://api.gptunrestricted.com/v1 and set your new key. The model ID is uncensored. Our endpoint matches the OpenAI standard.

Test with a single request. Streaming and JSON modes work immediately.

Stop paying for refusals.
Keep your existing client code.

Worked token cost examples for your budget

Calculate your spend using our transparent rates: $0.15 per million input tokens and $0.50 per million output tokens. If you send 50,000 input tokens and receive 4,000 output tokens, your total cost is just $0.00775. Errors and refusals incur zero charges, so you only pay for actual tokens generated. This prepaid model ensures no surprise bills. Use our calculator to estimate costs before sending requests to your uncensored LLM endpoint.

Checklist for choosing the right uncensored provider

Verify the billing model matches your usage patterns. Prefer prepaid tokens over subscriptions to eliminate surprise charges and monthly fees. Ensure the API is OpenAI-compatible so existing SDK code works without rewriting. Check that the context window supports your long-form needs, ideally 100k tokens. Confirm crypto-only top-ups if you want privacy. Avoid providers using your prompts for training. This API offers prepaid credit with no monthly subscription, a 100k context window, and no training on your data.

Who should use this API and who it is not for

Use this uncensored LLM when you need reliable, adult-friendly story generation or unrestricted reasoning without content blocks. It fits developers requiring a 100k context window and OpenAI-compatible tool calling. Do not use it if you need image or audio generation, or fine-tuning capabilities. It is also unsuitable for teams requiring SOC2 certifications or on-prem deployment. The service focuses purely on text completion via our tuned model, not a proxy for other vendors.

Common questions

What is the unrestricted GPT API?

It is an OpenAI-compatible endpoint for our uncensored model. POST /v1/chat/completions handles text generation. It supports streaming, JSON mode, and tools. You send the model id "uncensored" to access these features without content filters.

How much does it cost per million tokens?

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors and refusals are free. You pay prepaid credit based on real usage. No monthly fees or subscriptions apply to your account.

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.

What is the maximum context window size?

The context window is 100,000 tokens. This includes both prompt and completion. You can generate up to 16,000 tokens per request. Setting max_tokens is required to reach that limit. Shorter outputs default to 2,048 tokens.

Do you support streaming responses?

Yes, streaming is supported via Server-Sent Events. Token usage data appears in the final chunk. This allows real-time text display for your users. You can also use standard JSON mode for structured outputs.

Are prompts used for training my data?

No, your prompts are not used for training. Privacy is preserved by design. You only need an email for your account. You can use the API for sensitive content without worrying about data retention.

Get your API key

Open account View documentation