Uncensored LLM API
Models api for uncensored deployments
Get an open-weight uncensored model via our OpenAI-compatible API with a 100,000 token context window and transparent per-token pricing.
- 100,000 token context window
- OpenAI-compatible chat endpoint
- Crypto top-up only
Test with one calluncensored
curl https://api.modelsapi.cc/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List five python libraries for data visualization"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.modelsapi.cc/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.modelsapi.cc/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
OpenAI-Compatible
Drop-in replacement for existing clients using our base URL.
Long Context
Handle massive documents with a 100,000 token context window.
Function Calling
Native tool support with json_object response format capability.
Streaming Support
Real-time token delivery via Server-Sent Events with usage stats.
No Filters
Unrestricted output for lawful adult and creative use cases.
Instant Access
Start generating immediately with a Google login and no card.
Setup process
Create Account
Sign up with Google or email to get your key instantly.
Top Up Crypto
Add funds via USDT or USDC to activate your credit.
Call API
Send requests to the chat completions endpoint with your key.
Community projects
Content Generation
Produce unrestricted creative writing and NSFW stories without refusals.
Data Extraction
Parse large documents efficiently using the extended context window.
Agent Tools
Integrate reliable function calling into your autonomous AI agents.
Research Models
Test uncensored capabilities for security and content analysis tasks.
Why developers choose models API for uncensored generation
Developers choose models API because it delivers a single, dedicated uncensored model with transparent per-token pricing, avoiding the complexity of router-based multi-model services.
Reliable content freedom
Send text and get text without unexpected refusals for lawful adult topics.
Predictable billing
$0.15 per 1M input tokens and $0.50 per 1M output tokens.
Instant setup
Get a key via Google or email, then integrate immediately.
Migrate from OpenAI-compatible providers in three steps
Switch your uncensored LLM client in minutes by updating the base URL to HTTPS://api.modelsapi.cc/v1 and inserting your new API key. First, generate your key via Google or email login. Next, replace your existing endpoint configuration with our direct address. Finally, send a test request to /v1/chat/completions to verify connectivity. No routing fees or complex model selection required. The model ID is "uncensored".
Who needs unrestricted LLM generation and who should skip it
Developers building chat apps, roleplay bots, or research tools requiring unfiltered responses use our API. It fits projects needing 100k context windows without content refusals.
- Use it for creative writing or sensitive data analysis.
- Skip it if you need image generation, embeddings, or multi-model routing. We serve one specific model via a single base URL.
Cost breakdown: real token arithmetic for your budget
Uncensored API pricing is transparent: $0.15 per million input tokens and $0.50 per million output tokens. Errors cost nothing. A 10,000-token prompt generating 2,048 tokens uses 12,048 tokens total. This costs roughly $0.002. You pay for real usage. No hidden fees. Credit never expires. Add crypto to your account instantly. Calculate your exact budget before deployment. Avoid surprise charges with simple token counting.
Common pitfalls in the uncensored niche (and how we fix them)
Developers often waste time debugging unexpected refusals in supposedly uncensored models, or they assume all "abliterated" variants behave identically across different providers. Routing complexity adds latency and unpredictable billing structures that obscure true costs. We eliminate these variables by serving a single, dedicated model with transparent, per-token pricing. You get consistent, unfiltered outputs without the noise of multi-model routers or hidden tier limits.
The checklist for selecting an uncensored AI provider
Verify the model is truly abliterated, not just a standard Llama 40B with a loose safety layer. Confirm the base URL follows the OpenAI chat-completions standard for zero-friction SDK integration. Check that pricing is transparent per-token with no hidden subscription fees. Ensure crypto top-ups via USDT or USDC are straightforward. Verify the context window supports your data size.
Common questions
What is models API and how does it work?
It is an uncensored LLM API serving a single dedicated model via the standard OpenAI-compatible endpoint. You send requests to POST /v1/chat/completions and receive text responses without content filters.
What is the context window and token limit?
The model supports a 100,000 token context window for prompt and completion combined. You can request up to 16,000 tokens per output, or 2,048 tokens if you do not set max_tokens.
Does it support streaming and function calling?
Yes, it supports streaming via Server-Sent Events and includes function calling with tool definitions. You can also enforce JSON mode using the response_format parameter for structured data outputs.
How much does the API cost per token?
Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. Credit is charged only for real usage, and errors or refusals are completely free of charge.
What payment methods are accepted for top-ups?
We accept crypto only, specifically USDT on TRC20 or USDC on Base. Minimum top-ups start at $20, and you receive bonus credit for larger amounts like $100 or $200.
What are the rate limits for API keys?
Each key allows 300 requests per minute and up to eight simultaneous concurrent requests. The maximum request body size is 8 MB, and each account is limited to one active key.
Get your key now
Sign up, grab the key, update the base URL. Done.
