Drop-in Compatibility
LLM api proxy for uncensored generation
Swap your base URL for our uncensored LLM endpoint and generate text with a 100,000 token context window without subscription locks.
- 100,000 token context window
- 0.15 per 1M input tokens
- Crypto top-up only
Test with one request
- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
curl https://api.llmapiproxy.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Fetch the current temperature in Tokyo"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.llmapiproxy.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.llmapiproxy.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);Key features
OpenAI Compatible
Works with any OpenAI SDK by changing base_url and the API key.
Uncensored Model
Open-weight model tuned to answer without refusals for lawful adult use.
Streaming Support
Receive real-time token usage and text via standard Server-Sent Events.
JSON Mode
Enforce structured outputs with response_format json_object for reliable parsing.
Function Calling
Support tools and tool_choice for complex agent workflows.
No Subscription
Prepaid credit never expires and errors are free.
Setup process
Get Key
Sign up with Google or email to receive your API key instantly.
Top Up
Add credit via USDT or USDC with instant bonus tiers.
Connect
Update your base_url to our endpoint and start generating.
Common use cases
Content Generation
Produce unrestricted creative writing and adult fiction without content filters.
Research Agents
Run uncensored AI agents for security research and analysis.
Chatbots
Deploy NSFW chatbot interfaces that do not refuse topics.
Coding Assistants
Use the proxy as a Claude proxy alternative for code generation.
Uncensored vs. Standard: 4 Concrete Differences
We eliminate subscription locks by offering a pure prepaid token model with crypto checkout. Unlike typical gateways, we provide a single, uncensored model with transparent arithmetic and no hidden usage tiers.
| Feature | Our Proxy | Standard Gateway |
|---|---|---|
| Model | Single uncensored model | Multiple vendors |
| Billing | Prepaid tokens; errors free | Monthly subscription |
| Content | No refusals for lawful adult use | Strict filters |
| Setup | Drop-in OpenAI compatible API | Code changes |
Real Cost Arithmetic: Input vs. Output Tokens
Input tokens cost $0.15 per million, while output tokens cost $0.50 per million. A 10,000-token prompt with 1,000 output tokens generates 2.0 output tokens at $0.002. Errors incur zero charges. Use this LLM API proxy for predictable scaling without subscription surprises. Check the pricing page for full details.
LLM API proxy Use Cases for Developers
The LLM API proxy delivers high-volume, uncensored generation without vendor lock-in.
NSFW Chatbot Agents
Run adult-themed conversational agents that never hit a content refusal wall.
Security Research
Probe model boundaries with controversial prompts to map refusal patterns accurately.
Creative Writing
Generate unfiltered fiction and roleplay scenes without unexpected tone shifts.
Code Generation
Get raw code output without polite conversational filler or safety disclaimers.
Developer Questions: Limits, Billing, and Privacy
Developer Questions: Limits, Billing, and Privacy
Our uncensored LLM proxy charges only for actual token usage, with errors free.
You receive $0.50 trial credit instantly, no card needed.
Top-ups accept USDT or USDC via crypto only.
Each account allows one active API key.
Usage caps at 300 requests per minute and 8MB payloads.
Prompts stay private and never train the model.
Refunds are not issued, but mistakes are resolved via Support.
Migrate from OpenAI in Three Steps
Switch your base URL and API key to connect instantly.
- Update your client configuration to point to
https://api.llmapiproxy.com/v1. - Replace your existing key with the new credential from your dashboard.
- Send your first request to
/v1/chat/completions.
The same SDKs work without code changes. You keep your logic while gaining an uncensored endpoint with transparent token pricing and no monthly subscriptions.
Who Should Use This Proxy (And Who Shouldn't)
Use this proxy when you need uncensored generation without subscription locks. Developers benefit from drop-in OpenAI compatibility via the chat-completions endpoint. Prepaid credit prevents budget surprises, and crypto top-ups keep overhead low. Avoid us if you require embeddings, image generation, or model routing. Our single uncensored model lacks fine-tuning capabilities and does not support audio or video outputs. It is strictly for text-based workflows needing reliable, unfiltered responses.
Frequently asked questions
What is an LLM API proxy and how does it differ from a standard gateway?
It is a single, uncensored endpoint. Standard gateways often apply content filters or require monthly subscriptions. Our service uses a prepaid token model with crypto checkout. You get one model that answers without refusals for lawful adult use.
Does the proxy support streaming responses?
Yes. You can use Server-Sent Events (SSE) to receive tokens as they are generated. The final chunk includes the actual token usage statistics. This allows your application to display text in real-time without waiting for the entire completion.
What payment methods are accepted for topping up credit?
We accept only USDT (TRC20) and USDC (Base). Minimum top-ups start at $20. You receive bonus credit for larger amounts, ranging from +5% to +15%.
Is there a monthly fee or subscription required?
No. We charge only for the tokens you actually consume. Errors and refusals are free. Your prepaid credit never expires. This model eliminates the friction of recurring billing and vendor lock-in.
What are the request limits per API key?
You can send up to 300 requests per minute. The system allows 8 concurrent requests per key. Each request body is limited to 8 MB. These limits ensure stable performance for your automated workflows.
Does the model refuse content?
It refuses only one hard limit: sexual content involving minors. All other lawful adult, fictional, or controversial topics are answered. It is not GPT, Claude, or any other vendor model.
Get your API key
Register, retrieve your key, update the base URL. Simple setup.
