Pay per token
Getcheapai uncensored API
Save money with getcheapai, the uncensored LLM API that charges $0.15 per 1M input tokens and requires no minimum spend.
- $0.15 per 1M input tokens
- 100k token context window
- Streaming with SSE support
Uncensored API. Pay only for tokens.
- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Prepaid only. Funds do not expire after 7 days.
Test with one request
curl https://api.getcheapai.cc/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Generate 500 lines of dummy JSON data"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.getcheapai.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.getcheapai.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
Uncensored model
Get responses without refusals for lawful adult or creative content.
OpenAI compatible
Connect your existing SDKs by simply changing the base URL.
Streaming support
Receive real-time tokens via Server-Sent Events with usage data.
Function calling
Use tools and JSON mode for structured data extraction tasks.
No expiration
Prepaid credit never expires so you pay only for usage.
High limits
Process 300 requests per minute with a 16k token max output.
Setup guide
Create account
Sign up with Google or email to get an API key.
Add crypto credit
Top up with USDT or USDC to start making requests.
Send requests
Use the /v1/chat/completions endpoint to generate text immediately.
Use cases
Roleplay bots
Run character-driven chat apps without content filters blocking dialogue.
Code generation
Generate code snippets with full context windows for complex projects.
Creative writing
Produce long-form stories without sudden refusals or interruptions.
Data extraction
Parse structured JSON responses for automated backend workflows.
Real token math: how much $20 of credit actually buys you
Real token math: how much $20 of credit actually buys you
$20 buys 266,666 input tokens or 60,000 output tokens. This uncensored LLM costs $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals are free. You pay only for tokens used. Prepaid credit never expires.
- Input: 266,666 tokens
- Output: 60,000 tokens
getcheapai: your uncensored model for code, roleplay, and writing
getcheapai delivers a single, uncensored model optimized for high-volume text generation without content filters.
Code Generation
Send complex prompts to our 100,000-token context window and receive precise, refusal-free code outputs.
Roleplay
Create immersive characters with our open-weight model that handles adult themes and controversial topics freely.
Writing
Generate long-form articles or stories using streaming via SSE, paying only for tokens used.
Who gets value and who should keep looking
Developers needing uncensored text generation for code, roleplay, or creative writing get immediate value.
- High-volume users pay only for tokens used.
- No monthly commitments or subscription traps.
Keep looking if you need embeddings, image generation, or fine-tuning. This API serves one model via standard endpoints, so it fits projects requiring raw, filter-free output without extra features.
From signup to API key in three steps
Get your key instantly via Google or email. Create an account, retrieve your single active key, and configure your OpenAI-compatible SDK with the base URL. Send a POST request to chat completions. Start generating text immediately with zero configuration overhead.
- Sign up with Google or email.
- Copy your API key.
- Update your SDK base_url.
Developers ask: context windows, refusals, and streaming
How much context do we support?
Our uncensored LLM handles 100,000 tokens total. You get 16,000 output tokens per request.
Are responses streamed?
Yes, via Server-Sent Events. Token usage appears in the final chunk.
What content is refused?
We allow adult themes. We strictly block sexual content involving minors.
This approach ensures privacy without subscription traps. Getcheapai gives you raw access. temperature and top_p control randomness. Errors are free. No minimum spend applies.
Migrate from another provider in three clicks
Switch to getcheapai in three clicks. Update your base_url to https://api.getcheapai.cc/v1 and inject your new API key. Our endpoint accepts standard chat-completions payloads, so your existing client logic remains intact. Replace the model identifier with "uncensored" to access our open-weight model. You only pay for actual tokens, eliminating subscription traps.
Common questions
What is getcheapai and how does its pricing work?
It is an uncensored API charging $0.15 per million input tokens and $0.50 per output tokens. You pay only for real usage with prepaid credit that never expires. Errors are free.
Does it require a monthly subscription?
No. There is no monthly fee or minimum spend. You top up with crypto and only pay for tokens consumed. Unused credit remains available indefinitely until you use it.
What payment methods are accepted for top-ups?
We accept USDT (TRC20) or USDC (Base). You can add any whole amount from $20 to $500.
What is the maximum context window?
The model supports a 100,000 token context window for both prompt and completion. Max output is 16,000 tokens per request, or 2,048 tokens if you do not specify a limit.
Is there a free trial available?
Yes. Every new account receives $0.50 of trial credit valid for seven days. This allows you to test the API before purchasing more credit.
Are prompts used to train the model?
No. Your data remains private and is not used for training. The service requires only an email address, ensuring minimal account data collection while you generate text via the API.
Get your API key now
Sign up, grab your key, and update your endpoint URL. That is it.
