Developer-first API
Uncensored AI Models for Developers
Get a single dedicated uncensored LLM with 100,000 token context via our OpenAI-compatible API, billed transparently per token without subscription traps or hidden guardrails.
- 100,000 token context window
- $0.15 per 1M input tokens
- Crypto billing, no card needed
Test with one call
curl https://api.modelsaiuncensored.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "list all available endpoint urls"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.modelsaiuncensored.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.modelsaiuncensored.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
Works with official SDKs by changing base_url and API key.
No Refusals
Uncensored model answers without content filters for lawful adult use.
Streaming SSE
Real-time token usage streaming with JSON mode and tools.
Transparent Pricing
Prepaid credit charged by real usage; errors and refusals are free.
Crypto Payments
Top up with USDT or USDC plus bonus credit tiers.
Simple Limits
300 requests per minute with 8 MB request body max.
Setup process
Get Key
Sign up with Google or email to receive your API key.
Add Credit
Top up with crypto and receive bonus credit instantly.
Start Sending
Point your client to our base_url and begin streaming.
Common use cases
Content Generation
Produce unrestricted creative writing without political or sexual guardrails blocking output.
Data Annotation
Label data with an uncensored AI API that does not filter topics.
Chatbots
Build unfiltered chatbot interfaces that answer controversial questions directly.
Research
Run security research on model behavior without standard refusal patterns.
Who builds with us (and who shouldn't bother)
Developers needing reliable, uncensored LLM outputs for NSFW-tolerant automation build with us. We serve teams requiring direct model control without hidden guardrails. Your automation scripts get consistent responses. You do not bother here if you need image generation, embeddings, or multi-model routing. We offer a single uncensored model via standard chat-completions endpoints. This is a pure API, not a consumer chat app. Focus on your integration, not model selection.
Why most 'uncensored' APIs fail in production
Most uncensored APIs fail because they hide guardrails or charge for refusals. Models AI offers transparent per-token pricing with prepaid crypto billing. Errors and refusals are free. We serve one dedicated uncensored model via a standard OpenAI-compatible endpoint. You get predictable costs without subscription traps or hidden context limits that break long conversations.
Real-world use cases for uncensored AI models
We deploy uncensored AI models for automation that requires raw output without political or moral filtering.
Content Generation
Creators use the NSFW LLM to produce adult-themed narratives without sudden refusals interrupting their workflow.
Research Agents
Dev teams run unrestricted queries to analyze controversial topics without the model sanitizing the data.
Custom Chatbots
Build unfiltered chatbot interfaces for specific communities that demand direct answers to sensitive questions.
How our API differs from generic alternatives
Our API delivers a single, dedicated uncensored model without vendor routing or hidden guardrails. Unlike multi-vendor proxies, we offer transparent per-token billing with prepaid crypto, avoiding subscription traps. Errors and refusals are free, and credits never expire. You get a straightforward, developer-first experience with no complex integrations or hidden fees.
| Feature | Our API | Typical Alternative |
|---|---|---|
| Pricing Model | Prepaid crypto, per-token | Subscription or metered |
| Model Routing | Dedicated uncensored model | Multi-vendor proxy |
| Refusals | Free | Charged |
| Credit Expiry | Never expires | Monthly or annual |
Checklist for choosing an uncensored provider
Checklist for choosing an uncensored provider
Verify the model is dedicated, not routed through crowded proxies that add latency or hidden guardrails. Confirm pricing is strictly per-token with prepaid crypto billing, avoiding subscription traps. Ensure the API is OpenAI-compatible for easy integration. Check that context windows are sufficient for your use case, ideally 100k tokens. Finally, verify that refusals are rare for lawful adult content and that streaming is supported.
Migrate from your current provider in three steps
Switching to our uncensored LLM takes moments, not days. First, generate an API key via the dashboard. Next, update your client’s base URL to HTTPS://api.modelsaiuncensored.com/v1 and set the model ID to "uncensored". Finally, verify connectivity with a test request. Our OpenAI-compatible endpoint accepts standard parameters like temperature and top_p. No rewrites required. Billing resets instantly on prepaid credit. Start generating without guardrails today.
FAQ
What are uncensored AI models?
They are large language models that do not refuse lawful adult, fictional, security-research, or controversial topics. Our API serves one dedicated model that answers without content refusals for lawful adult use, ensuring unrestricted output for your specific needs.
How much does the API cost?
It costs $0.15 per 1M input tokens and $0.50 per 1M output tokens. You pay for real usage, so errors and refusals are free, with no monthly subscription fees or hidden costs attached to your prepaid credit.
Does the API support streaming?
Yes, it supports streaming via Server-Sent Events. You receive token usage details in the last chunk, allowing your application to display responses in real-time while maintaining compatibility with standard OpenAI-compatible clients and SDKs.
What is the context window size?
The context window is 100,000 tokens for both prompt and completion combined. You can generate up to 16,000 tokens per request, or 2,048 if you do not explicitly set the max_tokens parameter in your API call.
How do I pay for credits?
You top up using crypto only, specifically USDT on TRC20 or USDC on Base. We accept whole amounts from $20 to $500, and you receive bonus credit ranging from +5% to +15% depending on your deposit size.
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.
Get your API key
Sign up, copy your key, and update your base URL. Simple integration.
Claim trial key