Uncensored API

C.ai api: The Uncensored Alternative for Developers

Get an uncensored LLM API with a 100,000 token context window, direct OpenAI compatibility, and transparent crypto billing for unrestricted roleplay.

Try with trial credit View documentation

100k token context window

$0.15 per 1M input tokens

No training on your data

Test with one call

curl https://api.caiapi.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Get user_id 99 for account settings."}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.caiapi.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.caiapi.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);

$0.15per 1M input tokens

$0.50Output tokens / 1M

100,000token context

$0.50trial credit

300requests per minute

Core features

Uncensored Model

Open-weight model tuned for lawful adult content without refusals.

OpenAI Compatible

Works with official SDKs by changing base_url and API key.

Streaming Support

Get token usage in the last chunk via SSE streaming.

JSON Mode

Enforce structured output with response_format json_object parameter.

Function Calling

Use tools and tool_choice for dynamic agent interactions.

No Card Needed

Start with $0.50 trial credit valid for 7 days.

Setup guide

Sign Up

Use Google or email to get your API key immediately.

Top Up

Add crypto credit via USDT or USDC with bonus credits.

Integrate

Point your client to HTTPS://api.caiapi.cc/v1 and send requests.

Common use cases

Roleplay Bots

Run unrestricted character chats with long context for memory.

Adult Content

Generate NSFW text without filters for lawful adult use.

Research Agents

Deploy uncensored models for security research and creative writing.

Developer Testing

Test function calling and JSON modes with a simple API.

Uncensored API. No refusals. Pay per token.

Why the c.ai API is the Ultimate NSFW LLM Solution

The c.ai API delivers a single, uncensored model via a standard OpenAI endpoint, stripping away multi-model routing overhead. You get direct, unfiltered text generation with transparent crypto billing and no training on your data.

Roleplay Without Refusals

Send POST /v1/chat/completions with model "uncensored" and receive raw, unrestricted responses tailored for adult themes.

Developer-First Integration

Use our base URL with any OpenAI SDK. Set temperature, top_p, and seed parameters exactly as you prefer.

Predictable Costs

Pay $0.15 per 1M input tokens. No subscriptions. Just prepaid credit that never expires.

From Signup to First Token: How It Works

Sign up via Google or email; no phone number required.
Receive your API key instantly on the dashboard.
Set base_url to https://api.caiapi.cc/v1 and use model uncensored.
Send your first request.

Common Mistakes in Uncensored AI and How to Avoid Them

Developers often confuse creativity with logic, leading to poor problem-solving accuracy in roleplay contexts. Our uncensored LLM API prioritizes direct, unfiltered responses without unnecessary creative fluff. Another frequent error is assuming multi-model routing is essential; we provide a single, consistent model via the standard OpenAI endpoint, eliminating complex overhead. You get transparent crypto billing and no training on your data, ensuring your prompts remain private and your tokens count towards actual generation, not server fees.

Who This API Is For (And Who Should Look Elsewhere)

Developers building uncensored roleplay engines use this API for direct, unfiltered text generation without enterprise overhead.

Best for: RP bots needing 100k context, crypto users, and creators who want no data training.
Not for: Teams requiring image generation, embeddings, or multi-model routing.

If you need strict SLAs or video capabilities, look elsewhere. We offer raw, unrestricted LLM access via standard OpenAI endpoints.

How We Differ from Typical AI Gateways

Our uncensored LLM API strips away the overhead of multi-model routing and enterprise SLAs. You get direct, unfiltered text generation with transparent crypto billing and no training on your data.

Feature	Typical Alternative	Ours
Model Routing	Multi-vendor abstraction	Single uncensored model
Billing	Monthly subscription	Pay per token
Data Usage	Training on inputs	No training
Contracts	Complex SLAs	Simple terms

Migrate from Another OpenAI-Compatible Provider in 3 Steps

Switch to our uncensored LLM API by updating your base URL and model ID. First, change your SDK configuration to point to HTTPS://api.caiapi.cc/v1. Next, set the model parameter to "uncensored" for unrestricted generation. Finally, paste your new API key from the dashboard. Your existing code works immediately. No complex routing or extra setup required. Start generating text today.

Common questions

What is the c.ai API and how does it handle content?

It is an uncensored LLM API serving one open-weight model tuned for unrestricted output. Lawful adult, fictional, and controversial topics generate without refusals, except for sexual content involving minors which is always blocked.

Is this uncensored LLM API compatible with standard tools?

Yes. It uses the OpenAI-compatible chat-completions endpoint, so you can connect any existing SDK or client. Just update your base URL to HTTPS://api.caiapi.cc/v1 and provide your API key.

What are the context window limits for requests?

The model supports a 100,000 token context window for combined input and output. You can request up to 16,000 tokens per response, or 2,048 tokens if you do not specify a max limit.

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.

Does the API charge for errors?

No. You only pay for real token usage, meaning errors and refusals are free. Credit never expires, so you can use your balance over time without monthly fees or subscriptions.

Can I use the API for function calling and JSON mode?

Yes. The endpoint supports streaming via SSE, function calling with tools, and strict JSON mode. You can also control temperature, top_p, stop sequences, and seed for precise output generation.

Get your key in one step

Try with trial credit