Raw inference
Uncensored.com: The uncensored ai api you control
Get an uncensored AI API key with 100,000 token context windows and no monthly fees or vendor lock-in.
- Pay only for tokens used
- Crypto top-ups with bonus credit
- OpenAI-compatible endpoints
Test with one call
curl https://api.uncensoredcom.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Check if the server is online and responding correctly"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.uncensoredcom.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.uncensoredcom.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
Capabilities
OpenAI Compatible
Use standard SDKs with our base URL and API key for immediate integration.
No Refusal Model
The uncensored model answers controversial or adult topics without generic content filters.
Streaming Support
Receive real-time token data via Server-Sent Events for low-latency user experiences.
JSON Mode
Force structured output using response_format json_object for reliable programmatic parsing.
Tool Calling
Enable function calling capabilities with tool_choice and standard tool definitions.
No Expiry
Prepaid credit never expires so you can pause usage without losing funds.
Setup steps
Sign Up
Register with Google or email to receive your unique API key instantly.
Top Up
Add crypto credit via USDT or USDC to activate your account balance.
Integrate
Point your client to the base URL and start sending completion requests.
Common use cases
Content Generation
Generate unrestricted creative writing or roleplay scenarios without hitting standard content walls.
Data Extraction
Parse large documents using JSON mode for consistent structured data output.
Research Models
Test open-weight model behavior in controlled environments without external filter interference.
Custom Agents
Power autonomous agents with tool calling capabilities for complex multi-step tasks.
What developers actually ask about this topic
Yes, uncensored.com provides an uncensored LLM API via standard OpenAI-compatible endpoints. You send POST requests to /v1/chat/completions and receive raw text responses without arbitrary content filters for lawful adult use. The service supports streaming, function calling, and JSON mode. It handles 100k context windows and charges strictly by token usage. You pay $0.15 per million input tokens and $0.50 per million output tokens. Errors are free.
Why uncensored.com is the uncensored AI API of choice
We deliver raw, refusal-free inference via a standard OpenAI-compatible endpoint.
Zero Vendor Lock-in
Use any standard SDK with our base URL.
Transparent Pricing
Pay only for tokens consumed; errors cost nothing.
No Subscriptions
Crypto top-ups never expire. Your credit lasts forever.
Strict Privacy
Prompts stay yours. We do not train on your data.
The uncensored provider checklist: 6 steps to verify quality
Verify provider reliability by checking token pricing, model architecture, and content limits before committing.
- Confirm base URL: Ensure it is
https://api.uncensoredcom.com/v1for direct OpenAI compatibility. - Check context window: Verify support for 100,000 tokens without arbitrary truncation.
- Review refusal logic: Confirm only minor-related content is blocked, not general NSFW topics.
- Validate billing: Ensure prepaid credit never expires and errors are free.
- Test streaming: Verify Server-Sent Events support for real-time token delivery.
- Inspect limits: Check for 300 requests per minute per key.
Migrate from your current provider in three steps
Migrate from your current provider in three steps
Switch your base URL and API key to gain uncensored inference instantly. First, update your client configuration to point to HTTPS://api.uncensoredcom.com/v1. Second, set the model id to “uncensored” and adjust temperature settings as needed. Third, verify streaming works via SSE and test function calling. You retain your existing SDK integration while gaining raw, refusal-free generation for adult content.
Worked cost examples: exactly what you pay per token
You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. A 20,000-token request with 10,000 input and 10,000 output tokens costs $0.0065. Errors incur zero charges. Prepaid credit covers usage; no subscription fees apply. This transparent model ensures you only pay for actual inference, with credits never expiring and no hidden costs for refusals.
Common mistakes people make in this niche and how to avoid them
Common mistakes people make in this niche and how to avoid them
Developers often pay for refusals or assume unlimited context windows. Verify your POST /v1/chat/completions billing includes errors. Our uncensored AI platform charges zero for refused tokens, ensuring you pay only for actual generation. Avoid vendor lock-in by sticking to OpenAI-compatible SDKs. We do not offer embeddings, so remove those library calls. Check your max_tokens limit; it caps at 16,000 per request, not infinity. This transparency prevents surprise bills from generic providers.
Common questions
What is uncensored.com and how does the API work?
It is a hosted, OpenAI-compatible service for text generation. You send prompts and receive text outputs via standard endpoints. The base URL is HTTPS://api.uncensoredcom.com/v1. This setup allows you to use existing SDKs without rewriting your integration logic.
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.
How much does the uncensored LLM API cost per token?
Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. You only pay for actual usage. Errors and refusals do not incur charges. This transparent pricing ensures you know exactly what you spend before you send requests.
What payment methods are accepted for topping up credit?
We accept only USDT (TRC20) or USDC (Base). Minimum top-ups start at $20. You can add up to $500 per transaction. Crypto payments ensure fast processing without bank delays or third-party payment processor fees.
Does the API support streaming responses?
Yes, it supports streaming via Server-Sent Events. You receive real-time token updates as they are generated. Token usage details appear in the final chunk. This feature works seamlessly with standard OpenAI-compatible client libraries for efficient data handling.
What is the maximum context window size?
The model supports a 100,000 token context window. This includes both your prompt and the generated completion. You can request up to 16,000 tokens per output. If you do not specify max_tokens, the limit defaults to 2,048 tokens.
