Uncensored LLM API
Claude proxy: The uncensored alternative
Get a drop-in uncensored LLM API with a 100,000 token context window, transparent pricing, and zero vendor lock-in for your next project.
- 100,000 token context window
- $0.15 per 1M input tokens
- No subscription required
curl https://api.proxyclaude.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "list all python packages installed in the current virtual environment"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.proxyclaude.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.proxyclaude.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);- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
Features
OpenAI compatible
Works with existing OpenAI SDKs and any standard client.
No refusals
Answer without content filters for lawful adult or creative use.
Streaming support
Get token usage in the last chunk via standard SSE.
JSON mode
Enforce structured outputs with simple response_format configuration.
Crypto payments
Top up with USDT or USDC and get bonus credit.
No hidden fees
Pay only for real token usage, not for errors.
Setup steps
Generate your key
Sign up with Google or email to get an API key instantly.
Update your base URL
Point your client to HTTPS://api.proxyclaude.com/v1 and set the key.
Send requests
Post to /v1/chat/completions using the model id "uncensored".
Use cases
Creative writing
Generate unrestricted narratives without standard content filters blocking your ideas.
Code generation
Write complex code snippets with high token capacity for large files.
Research analysis
Process long documents within the 100,000 token context window efficiently.
Adult content workflows
Serve uncensored responses for lawful adult themes without extra costs.
Real token math: see exactly what your prompt costs
Your prompt costs are transparent. Input tokens run $0.15 per million, while output tokens charge $0.50 per million. Errors and refusals cost nothing. A 10,000-token request with 2,000 output tokens totals $0.0065. No hidden fees apply. You pay only for tokens actually consumed. This model eliminates billing surprises for developers seeking predictable spending on uncensored workflows.
From zero to first response: 4-step integration guide
From zero to first response: 4-step integration guide
Start using our uncensored LLM in under five minutes by following these straightforward steps.
- Sign up with Google or email to receive your API key instantly.
- Set your base URL to
https://api.proxyclaude.com/v1. - Send a POST request to
/v1/chat/completionsusing the model IDuncensored. - Receive your first text response with transparent token usage.
claude proxy use cases: roleplay, coding, and research
Our uncensored LLM handles roleplay, coding, and research without the standard refusals that plague other providers.
Roleplay and Creative Writing
Generate long-form narratives with consistent character voices and adult themes, ensuring no content filters interrupt your creative flow.
Coding and Debugging
Execute complex code generation tasks and debugging sessions, leveraging our 100,000-token context window to maintain project context across thousands of lines.
Research and Analysis
Analyze large datasets or documents with high precision, receiving direct answers without the polite hedging common in filtered models.
Common proxy pitfalls: how to avoid bad responses and hidden costs
Bad responses often stem from ignoring context windows. Ensure your prompt fits within 100,000 tokens. Hidden costs appear when proxies charge for refusals. Our API bills only consumed tokens, making errors free. Avoid repetitive outputs by adjusting temperature. Check rate limits strictly. Use streaming to handle large payloads efficiently. Verify your client SDK matches the endpoint structure. Always test with small samples first.
Proxy vs. direct: 6 signs you are overpaying or under-delivered
You likely waste money on hidden refusals or pay for unused capacity.
The uncensored API buyer checklist
Verify true uncensoring
Test with controversial topics to confirm refusals are gone.
- Check for hard limits like minor content.
- Ensure streaming via SSE works reliably.
- Confirm JSON mode and function calling are active.
Validate pricing transparency.
- Confirm $0.15/$0.50 per 1M tokens.
- Ensure errors cost zero tokens.
- Verify prepaid credit never expires.
Assess infrastructure limits.
- Check the 300 requests per minute cap.
- Confirm 100,000 token context window.
- Ensure crypto-only top-ups match your workflow.
Frequently asked questions
What is the claude proxy and how does it differ from official APIs?
It is a hosted service routing requests through a single uncensored model via an OpenAI-compatible endpoint. You get one model id, not multiple choices. This eliminates complex routing and ensures predictable token pricing without subscription lock-in.
Does the uncensored model refuse content?
No, it answers without refusals for lawful adult use, but strictly blocks sexual content involving minors. You receive text in and text out with no hidden fees for refusals, ensuring transparent billing for every request.
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.
Can I use standard OpenAI SDKs with this service?
Yes, the endpoint is fully compatible with official OpenAI SDKs and any compatible client. You simply update the base URL to HTTPS://api.proxyclaude.com/v1 and provide your API key for immediate integration into your workflow.
What is the context window size?
The model supports a 100,000-token context window for both prompt and completion together. You can specify a max output of 16,000 tokens per request, or default to 2,048 tokens if you do not set the limit.
How much does the API cost per token?
Input tokens cost $0.15 per million, while output tokens cost $0.50 per million. Errors and refusals are free, and prepaid credit never expires, so you only pay for the actual tokens used in successful requests.
