Uncensored Inference API
Inference api for uncensored LLM integration
Deploy our uncensored LLM via a standard openai compatible API with 100,000 tokens context window and transparent per-token pricing for NSFW workloads.
- 100,000 token context window
- No refusals on adult topics
- Crypto top-ups with bonus credit
Test with one call
https://api.apiinference.com/v1curl https://api.apiinference.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Fix the syntax error in this Python function"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.apiinference.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.apiinference.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
Uncensored by default
Answers without refusals for lawful adult content, fiction, and research topics.
OpenAI compatible interface
Works with your existing SDKs by changing the base URL and key.
Large context window
Process up to 100,000 tokens including prompt and completion together.
Streaming with usage
Receive real-time tokens and final usage stats via Server-Sent Events.
JSON mode support
Force structured output for reliable data parsing in your SaaS applications.
Crypto-friendly payments
Top up with USDT or USDC and receive bonus credit instantly.
Setup workflow
Create your account
Sign up with Google or email to receive your API key instantly.
Add crypto credit
Top up with USDT or USDC to start sending requests immediately.
Send your first request
Point your client to our base URL and start generating text.
Integration patterns
NSFW Chat Applications
Build adult-oriented chatbots that do not block popular tropes or themes.
Data Extraction Pipelines
Parse complex documents with JSON mode and a large context window.
Content Generation Tools
Generate creative fiction or roleplay without unnecessary safety filter interruptions.
Research Assistants
Query controversial or niche topics without the model refusing to answer.
Why your next inference API needs to be uncensored
Our inference API removes content refusals so your application generates complete responses without blocking lawful adult or controversial topics.
Unfiltered creative writing
Send prompts for mature themes and receive full narratives without arbitrary filters blocking your output. This ensures consistent story generation for adult-oriented SaaS products.
Security research workflows
Query the model for sensitive security findings or controversial data without triggering standard safety layers. You get raw analysis tailored to your specific use case.
Direct integration
Connect using the standard OpenAI compatible interface and get immediate results. No complex routing or extra model selection logic is required for your pipeline.
How to select the best inference provider for your needs
Start by verifying OpenAI compatibility to ensure your existing SDKs work without rewrite. Check that the uncensored LLM offers a 100,000 token context window for long-running tasks. Confirm transparent per-token pricing with no hidden subscription fees. Verify crypto top-up options and that errors remain free. Ensure the provider does not retrain your data. Confirm there are no model routing surprises. Finally, test the API key generation process for speed and simplicity.
Get started in 3 steps: Signup, Key, First Request
Obtain your API key and send your first uncensored request in under two minutes.
- Click Continue with Google or use email/password to create an account; no phone number is required.
- Your unique API key appears immediately on the dashboard for instant copying.
- Send a
POST /v1/chat/completionsrequest tohttps://api.apiinference.com/v1with model"uncensored"to receive text output.
Migrate from OpenAI or Grok in three easy steps
Swap your provider in minutes by pointing your SDK to our base URL. Update your client configuration to use the uncensored model ID and replace your existing API key with one from our dashboard. Our interface remains fully OpenAI-compatible, so your code works without changes. Switch to an uncensored LLM that answers without refusals and starts at $0.15 per million tokens. No complex routing, just direct inference.
Common Inference Pitfalls: Context Limits and Refusals
Developers often crash apps by exceeding the 100k token context or sending uncapped requests that hit the 16k output limit. Our uncensored model removes arbitrary refusals, ensuring consistent text-in, text-out behavior for lawful adult content. Avoid the 404 errors by verifying your base_url. Stream responses via SSE to handle large outputs gracefully. Keep payloads under 8 MB. This approach prevents unexpected billing spikes and ensures your SaaS integrates reliably without complex routing logic.
Calculate your costs: Token arithmetic for cheap inference
Calculate your costs: Token arithmetic for cheap inference
Predict your spend by multiplying token counts by $0.15 per 1M input tokens and $0.50 per 1M output tokens. For a typical 5,000-token prompt generating 2,000 tokens, you pay $0.775 total. This transparent per-token pricing ensures you know exactly what every request costs without hidden subscription bloat. Errors are free, so you only pay for successful completions. Keep your context window under 100,000 tokens to avoid unnecessary overhead while maintaining high-volume efficiency.
Common questions
What is an inference API?
It is a hosted endpoint for text generation. Ours accepts POST /v1/chat/completions and returns text. The uncensored model id is "uncensored". It handles 100,000 token context windows efficiently, allowing complex data parsing without external routing 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 do I get started with the inference API?
Sign up with Google or email to get an immediate API key. Send requests to HTTPS://api.apiinference.com/v1. Use the official OpenAI SDKs with your key. Top up with crypto like USDT or USDC starting at $20.
Does it support streaming responses?
Yes, streaming via Server-Sent Events is supported. You receive token usage statistics in the final chunk. This allows real-time rendering of text in your application while maintaining standard OpenAI-compatible client behavior for ease of integration.
What are the rate limits?
You can send 300 requests per minute per key. Concurrently, you can have 8 requests active simultaneously. The request body limit is 8 MB. These limits ensure stable performance for high-volume SaaS applications without unexpected throttling.
Can I use crypto for top-ups?
Yes, we accept USDT on TRC20 or USDC on Base. Minimum top-up is $20. Bonus credit applies: +5% from $50, +10% from $100, +15% from $200. Credit never expires and errors are free.
Generate your key now
Sign up, copy the key, update your base URL. That is the entire configuration.
