Uncensored LLM API
Uncensore ai: The uncensored API for developers
Get a single uncensored AI model with 100,000 token context for your NSFW LLM API needs, paying only for tokens with prepaid crypto.
- 100,000 token context window
- $0.15 per 1M input tokens
- OpenAI-compatible chat endpoint
curl https://api.uncensoreai.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "fetch the current server status from the api endpoint"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.uncensoreai.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.uncensoreai.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);Core features
- uncensoreai.com › 01
OpenAI Compatible
Use standard SDKs with base_url change and your API key.
- uncensoreai.com › 02
Prepaid Crypto
Top up with USDT or USDC for bonus credits on larger amounts.
- uncensoreai.com › 03
Streaming Support
Receive tokens via SSE with usage data in the final chunk.
- uncensoreai.com › 04
Tool Calling
Execute functions and tools with flexible tool_choice parameters available.
- uncensoreai.com › 05
JSON Mode
Force structured outputs using response_format for reliable data parsing.
- uncensoreai.com › 06
No Refusals
Answer without content filters for lawful adult and creative topics.
Getting started
Create Account
Sign up with Google or email to get your key instantly.
Top Up Credit
Send crypto to receive bonus credits that never expire.
Start Coding
Point your SDK to our base URL and send requests.
What builders create
Character Roleplay
Maintain consistent character voices without sudden topic refusals or resets.
Adult Content Gen
Generate mature themes freely without hitting standard safety filters.
Data Extraction
Parse large documents using JSON mode for reliable structure.
Creative Writing
Write uncensored stories with long context windows for continuity.
How this differs from a typical alternative on 4-6 concrete signs
We provide a single uncensored model via an OpenAI-compatible endpoint, unlike multi-vendor aggregators that route requests unpredictably. Our prepaid credit system charges strictly for real token usage, eliminating hidden subscription fees or tier restrictions. Crypto top-ups offer tangible bonuses, and errors remain free.
Who uses it, in which real situations; and plainly who it is NOT for
Developers building NSFW-tolerant chatbots use this uncensored LLM API to maintain character consistency without unexpected refusals. You will appreciate it for creative writing or roleplay where context windows of 100k tokens preserve long-term memory. It is NOT for teams needing image generation, embeddings, or multi-model routing. This is a single open-weight model API for developers who prioritize low cost and predictable billing over complex features.
uncensore AI: Concrete use cases for NSFW-tolerant generation
The uncensore AI API delivers reliable, refusal-free text generation for adult, controversial, and creative projects without arbitrary content filters.
Roleplay and Character Consistency
Maintain persistent personas across long contexts. The 100k token window keeps history intact without resetting.
Adult Content Creation
Generate NSFW stories or descriptions. The model handles mature themes without standard refusals.
Security Research
Probe model boundaries. Access raw outputs for jailbreak testing without hidden restrictions.
Uncensored Data Generation
Create diverse training data. Use the open-weight model for unbiased, direct text output.
Worked cost examples with token arithmetic that use only our prices
Your bills reflect real usage. We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. A 10k token prompt costs $0.0015. A 10k token response costs $0.005. Errors are free. Errors cost nothing. Errors are free. Errors cost nothing. Prepaid credit never expires. Errors are free. Errors cost nothing. Errors are free. Errors cost nothing. Errors are free. Errors cost nothing.
What developers actually ask about this topic
Does it reset context?
Our 100k context window preserves conversation history without arbitrary resets, ensuring consistent character behavior over long sessions.
Is it truly uncensored?
The model answers lawful adult and controversial topics without refusal, except for minor sexual content.
How do I pay?
We accept only crypto top-ups from $20 to $500, offering bonus credit for larger amounts.
Are there hidden fees?
You pay strictly for tokens used; errors and refusals are free, with no monthly subscriptions.
Common mistakes people make in this niche and how to avoid them
Developers often overlook context limits, causing unexpected truncation in uncensored AI workflows. We cap output at 16,000 tokens, so define max_tokens explicitly. Another error is assuming streaming skips billing; we charge only for completed tokens. Avoid hidden costs by monitoring usage via the final SSE chunk. Finally, do not confuse our single open-weight model with multi-vendor routing. Stick to our 100k context window for consistent NSFW-tolerant generation without complex integrations.
Common questions
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.
Is there a monthly subscription fee?
No. You pay only for tokens used. Credits never expire. Errors cost nothing. You top up with crypto when needed. There are no recurring charges or hidden tier restrictions for your account.
What payment methods are accepted?
We accept USDT on TRC20 or USDC on Base. Minimum top-up is $20. You get bonus credit for larger amounts.
Does the API support streaming responses?
Yes. You can enable streaming via Server-Sent Events. Token usage details appear in the final chunk. This allows real-time output display. It works with standard OpenAI SDKs by setting the stream flag.
What is the context window limit?
It supports 100,000 tokens total. This includes both prompt and completion. You can request up to 16,000 output tokens. This limit ensures long conversations remain consistent without memory loss.
Is there a trial available?
Yes. New accounts get $0.50 free. This credit lasts seven days. It allows testing before you buy crypto credits. Use it to verify integration speed.
Get your API key in seconds
Register, copy your key, and update your base URL. Setup is complete.
