Uncensored API

Obliterated llm for developers

Deploy a truly uncensored LLM via the standard OpenAI-compatible interface with a 100,000 token context window for robust creative applications.

Get your key View documentation

Prepaid credit, no subscriptions.
Zero refusals for adult content.
Crypto top-up only.

Test in one call

curl https://api.obliteratedllm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "return json with keys name and age"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.obliteratedllm.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.obliteratedllm.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

Key features

OpenAI Compatible

Drop into existing codebases by updating base_url and API key.

Uncensored Model

Receives prompts without the typical polite refusals found in other models.

Large Context

Process up to 100,000 tokens per request for deep analysis.

Streaming Support

Receive real-time tokens via Server-Sent Events with usage metadata.

Tool Use

Execute functions with JSON mode and tool_choice parameters.

Transparent Pricing

Pay only for tokens used; errors do not incur charges.

Setup guide

Generate Key

Update Base URL

Point your SDK client to HTTPS://api.obliteratedllm.com/v1 instead of the default.

Send Request

Call chat.completions with model id 'uncensored' and your prompt.

Common use cases

Roleplay Engines

Run character-driven narratives without content filters interrupting the immersion.

Creative Writing

Generate edgy or mature themes without manual post-processing or workarounds.

Red Teaming

Stress test other models by comparing their refusal rates against ours.

Data Generation

Produce large datasets of uncensored text for training or fine-tuning.

Migrate to uncensored inference in three steps

Switch your provider by updating your base URL and model ID. First, sign up and grab your key. Second, set the endpoint to HTTPS://api.obliteratedllm.com/v1. Third, change your model parameter from gpt-4 to uncensored. That is it. Your existing OpenAI SDK code works immediately. No complex routing logic required. Get started with a free trial.

obliterated LLM: uncensored, unhinged, and ready for production

Our API serves a single, dedicated uncensored model via the standard OpenAI SDK interface, eliminating the guesswork of provider routing or model selection. Use it for roleplay, creative writing, or NSFW applications without content refusals.

Direct Integration

Point your client at our base URL and start sending requests immediately.

Streaming Support

Receive real-time tokens via SSE for instant feedback in your UI.

No Routing Logic

Stop guessing which model handles your prompt. We handle the inference.

What developers actually ask about this topic

Our uncensored LLM API works exactly like OpenAI but without the refusals. Use the standard chat-completions endpoint with model id "uncensored". We accept 100k token context windows and support streaming. Pricing is prepaid: $0.15 per million input tokens and $0.50 per million output tokens. Errors are free. You get one API key per account. Crypto top-ups only via USDT or USDC. No monthly subscriptions. Scale usage without commitments. The model answers controversial topics directly.

Worked cost examples with token arithmetic

Our pricing is transparent and prepaid with no subscriptions, allowing you to scale usage without monthly commitments.

Typical request: 5,000 input tokens ($0.00075) plus 1,000 output tokens ($0.00050) totals $0.00125.
Long context: A 50,000-token input costs $7.50.

Credit never expires, so you can test thoroughly before committing to production workloads.

Common mistakes people make in this niche

Developers often assume 'uncensored' means infinite context, but this API caps outputs at 16,000 tokens despite a 100k window. Others ignore the prepaid model, expecting monthly bills; here, credit never expires. A frequent error is sending complex JSON without setting response_format, causing parsing failures. Don't forget that streaming via SSE includes usage data only in the final chunk. Finally, avoid mixing keys, as one active key per account replaces the old one immediately.

A checklist for choosing a provider in this niche

Verify uncensored behavior

Send a provocative prompt. Does it refuse?
Check token limits. 100k context helps.
Confirm OpenAI compatibility. Use standard SDKs.
Review pricing. Pay only for tokens.

Ensure no hidden fees. Test streaming support. Verify API key generation is instant. Avoid providers with complex routing. This checklist ensures reliable, direct access to an uncensored model without vendor lock-in.

FAQ

What is the obliterated LLM and how does it differ from standard models?

It is a dedicated uncensored model. It answers controversial topics without refusals. Standard models often block adult content. This API serves one open-weight model. It is not GPT, Claude, or Gemini. It is built for raw, unfiltered generation.

Does this service support streaming responses?

Yes, it supports streaming via Server-Sent Events. You can receive tokens as they generate. The final chunk includes usage data. This allows real-time display in your application. Use the standard OpenAI SDK to enable streaming easily.

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.

Can I use this API with Python or Node.js?

Yes, it is fully OpenAI-compatible. You can use the official SDKs. Change the base URL to the API endpoint. Use the model id uncensored. It works with any compatible client. Integration is straightforward and standard.

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 only for real usage. Prepaid credit never expires. This model offers transparent, predictable pricing.

What is the context window size?

The context window is one hundred thousand tokens. This covers both prompt and completion. You can set max output to sixteen thousand tokens. Default output is two thousand four hundred eight tokens. Large context enables deep analysis.

Get your API key

Get your key