Direct API Access
Unlocked Models: The Uncensored LLM API
Get immediate, uncensored API access to our uncensored models with a 100,000-token context window for unrestricted text generation.
- $0.15 per 1M input tokens
- Stream via SSE with tools
- No card required to start
Test the endpoint
curl https://api.modelsunlocked.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Set the server port to 8080 and restart"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.modelsunlocked.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.modelsunlocked.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);Platform capabilities
OpenAI-Compatible Interface
Use standard SDKs by simply changing the base URL to our endpoint.
100k Context Window
Process long documents with a 100,000-token limit for prompt and completion.
Crypto Payments Only
Top up with USDT or USDC and receive bonus credit on larger deposits.
Streaming Support
Receive real-time tokens via Server-Sent Events with usage data in the final chunk.
JSON Mode
Enforce structured output formats using the response_format parameter for reliable parsing.
No Training Used
Your prompts remain private and are not used to train our model.
Setup workflow
Create Account
Sign in with Google or email to get your key instantly.
Add Crypto Credit
Top up with USDT or USDC to start sending requests immediately.
Send Requests
Use your key with any OpenAI-compatible client to generate text.
Integration examples
NSFW Content Generation
Generate adult-oriented creative writing without artificial content filters or refusals.
Unrestricted Research
Analyze controversial topics or security data without model-specific bias restrictions.
Roleplay Applications
Build immersive character bots that maintain persona without sudden tone shifts.
Long Context Analysis
Process large codebases or documents within the 100,000-token context window.
Why Developers Choose Unlocked Models for NSFW Projects
Unlocked models eliminate content refusals, giving you unrestricted access for NSFW projects without enterprise overhead. We provide a single, uncensored LLM via a standard OpenAI-compatible interface, ensuring your application receives direct answers for lawful adult use. This approach removes the complexity of model routing and the restrictions of mainstream providers, allowing you to focus on building.
Consistent NSFW Output
Get reliable text responses without arbitrary filters blocking adult themes.
Direct API Access
Use standard SDKs with our base URL for immediate integration.
Transparent Pricing
Pay per token with no monthly fees or hidden costs.
7 Steps to Verify Your Uncensored API Provider
Verify Provider Specifics
- Check Token Limits: Confirm the exact input/output token counts.
- Test Streaming: Ensure SSE support for real-time token delivery.
- Review Pricing: Verify per-token costs match your budget.
- Assess Speed: Measure latency under load to ensure reliability.
- Confirm Privacy: Check if prompts are used for training.
- Check Payment Options: Ensure crypto payments are supported.
- Review Refund Policy: Understand credit expiration and refund rules.
Who Uses Unlocked Models (And Who Should Look Elsewhere)
Users needing standard model routing should look elsewhere.From Signup to First Token: How It Works
Get Your Key
- Sign up with Google or email. No phone number required.
- Get your API key instantly. It appears on screen immediately.
- Top up via crypto (USDT or USDC) starting at $20.
- Send a POST request to
POST /v1/chat/completions. - Receive text output with real-time token usage.
Transparent Token Arithmetic: Real API Costs
Your bill reflects exact usage at $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors cost nothing. A 10,000-token prompt with a 2,000-token response totals 0.0014 tokens, costing roughly $0.0025. Prepaid credit never expires, so small usage scales efficiently. We charge by real token consumption, not arbitrary limits. This model suits developers who need precise cost control for uncensored AI projects without hidden fees or monthly subscriptions.
How Our Uncensored API Differs from Standard Alternatives
We provide a single, uncensored LLM via a standard OpenAI-compatible interface, eliminating the complexity of model routing and the restrictions of mainstream providers.
Technical FAQs
What are unlocked models in the context of this API?
Unlocked models refer to our single, uncensored LLM that answers without content refusals. It serves lawful adult content via a standard OpenAI-compatible interface. The model id is "uncensored" and runs on our own servers.
Does the API support streaming responses?
Yes, the API supports streaming via Server-Sent Events (SSE). Token usage details are included in the final chunk of the stream. This allows real-time text generation for your applications without waiting for full completion.
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 context window size?
The context window is 100,000 tokens. This total includes both the prompt and the completion. There is no separate output cap: a response can use all the room left in the window.
Does the model refuse all NSFW content?
No, the model does not refuse lawful adult topics. It only enforces a hard limit on sexual content involving minors. This makes it ideal for NSFW projects requiring unrestricted fictional or adult creative writing capabilities.
What happens if I make an error request?
Errors and refusals are free. You only pay for actual tokens used. If you encounter a double charge, you can fix it through the Support page. Credit is not refunded but remains valid indefinitely.
Access requires one step
Register, retrieve your token, and update the base URL. Complete.
Guides
Practical articles on setup, pricing and integration.
Unlocked Models API: Setup With the OpenAI SDKSet up an unlocked models API with the OpenAI SDK in Python, Node or curl: base URL, key, model id, first call, streaming and what unlocked means…
What Do Unlocked AI Models Mean? Definition and LimitsUnlocked models explained: what the term means, how they differ from vendor-aligned models, common use cases, real limits and what stays off the…NSFW Models: Production Checklist for Uncensored LLM APIsUse this checklist to select the best NSFW models API. Verify uncensored content, OpenAI compatibility, and transparent pricing for your AI project.