EN ▾
Get API key

Raw Text API

uncensored LLM API for raw output

Access a single, abliterated large language model via standard OpenAI-compatible endpoints. Get uncensored, lawful adult outputs without managing GPUs or content filters.

Get API keyRead the docs

  • 100k token context window
  • $0.15 per 1M input tokens
  • $1 trial, no card required

Try it in one request

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

What you get

OpenAI-Compatible Endpoints

Use POST /v1/chat/completions with streaming and tool calling. Works with official OpenAI SDKs by changing the base URL.

Single Uncensored Model

We serve one open-weight model tuned to answer without refusals. It is not GPT, Claude, or Gemini.

Transparent Usage Pricing

Pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. No monthly fees or subscriptions.

Zero Training on Data

Your prompts are used only for inference. We do not train on your data or retain it for model improvement.

Instant API Access

Sign up with email and password. Receive your API key immediately. Regenerate keys instantly to revoke old ones.

Simple Rate Limits

300 requests per minute per key. 8 MB request body limit. Straightforward limits for consistent performance.

How it works

  1. Create Account

    Sign up with email and password to receive your unique API key.

  2. Add Credit

    Purchase prepaid credit by crypto (USDT on TRC20, USDC on Base). Start with $20 or use the free trial.

  3. Make Requests

    Send text to our API using your preferred language SDK and receive raw responses.

What people build with it

Raw Data Processing

Extract information from documents without content filters interfering with standard terms. Ideal for bulk text analysis where nuance matters more than safety rankings.

Coding Assistants

Generate code snippets without refusals for niche libraries or specific syntax styles. Useful for agents that need consistent, unfiltered code output.

Roleplay Applications

Power character-driven chats with models that do not block mature or controversial dialogue. Maintain narrative consistency without sudden tone shifts.

Security Research

Probe model boundaries and behavior without pre-filtering of common topics. Analyze how the model handles edge cases in controlled environments.

Why Uncensored Matters

Commercial models often refuse lawful content due to broad safety filters. This can disrupt applications that require consistent tone or specific vocabulary. Our model is abliterated to answer questions about adult topics, politics, and controversial subjects without refusal. This ensures your application receives the full text response you expect, not a polite denial. You retain full control over how to use the output.

For developers building chatbots or data pipelines, unexpected refusals are a major pain point. An uncensored llm provides a reliable baseline for text generation. You do not need to guess why a model stopped responding. The output is direct and complete, making it easier to parse and use in downstream processes.

OpenAI-Compatible API

We provide a standard chat-completions endpoint that integrates with existing tooling. Use the official OpenAI SDKs or any compatible client by updating the base URL to https://api.bestuncensoredllm.com/v1. The model id is "uncensored". This allows you to switch from other providers with minimal code changes.

The API supports streaming responses via Server-Sent Events and function calling. You get raw text input and output. There are no embeddings, image generation, or audio processing. This simplicity reduces complexity and cost. You pay only for the text tokens you use, not for unused features.

  • POST /v1/chat/completions for inference
  • GET /v1/models for listing
  • Streaming and tool calling supported

Pricing: Pay Per Token

Our pricing is straightforward and usage-based. You pay $0.15 per 1 million input tokens and $0.50 per 1 million output tokens. There are no monthly subscriptions or hidden fees. Prepaid credit does not expire, so you can use it whenever you need it.

Top-ups start at $20. You can pay by crypto (USDT or USDC). We offer bonus credits: +5% for $50 top-ups, +10% for $100 top-ups and +15% for $200 top-ups. New accounts receive $0.50 in trial credit valid for 7 days. Claim this credit with one click on your API key page. No credit card is required to start. This low barrier makes it easy to test the model before committing funds.

No Training, Pure Privacy

Your data privacy is a core feature. We do not use your prompts to train the model. Your conversations are processed for inference and not retained for model improvement. This is critical for applications handling sensitive data or proprietary content.

Signup requires only an email and password. No phone number or payment method is needed for the trial. You can regenerate your API key at any time, instantly revoking the old one. This gives you full control over access. We do not sell your data or use it for advertising. Your usage is purely for your own applications.

Questions and answers

Is this the best uncensored llm for coding?

This model is optimized for raw text output without refusals. It works well for coding tasks where standard models might block niche syntax or errors. It is not a specialized code model but a general uncensored llm that handles code generation reliably.

How much does it cost to use the API?

Input tokens cost $0.15 per 1 million tokens. Output tokens cost $0.50 per 1 million tokens. There are no monthly fees. You pay only for what you use. New users get $0.50 in free trial credit. Claim this credit with one click on your API key page.

Does this model have a context window limit?

Yes, the context window is 100,000 tokens. This includes both the prompt and the completion. Ensure your inputs fit within this limit to avoid truncation.

What content is blocked?

We block sexual content involving minors. This is the only hard content limit. All other lawful adult, political, or controversial topics are allowed. We do not filter based on tone or opinion.

Can I use this for roleplay?

Yes, the model is designed to avoid refusals for mature topics. It is suitable for roleplay applications that require consistent character voice without sudden safety interruptions. It is an uncensored ai model for creative writing and chat.

Your key is one form away

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

Get API key

Guides

Practical articles on setup, pricing and integration.

All guides →