Standard endpoints
POST /v1/chat/completions and GET /v1/models for easy integration.
Use our uncensored LLM API with 100,000 token context to run adult code and chat bots with standard OpenAI clients.
- $0.15 per 1M input tokens
- Prepaid crypto only, no card
- Streaming with token usage counts
Test with a single request
curl https://api.claudeapiproxy.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "get the current server time in ISO format"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.claudeapiproxy.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.claudeapiproxy.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);$0.15
per 1M input tokens$0.50
Output tokens / 1M100,000
token context$0.50
trial credit300
requests per minuteIncluded features
Large context
Handles 100,000 token context windows for long document processing.
Streaming support
Real-time token usage counts delivered in the final SSE chunk.
JSON mode
Enforce strict JSON output structures for reliable programmatic parsing.
Function calling
Execute external tools with standard tool_choice and tools parameters.
No training
Prompts are never used to train the underlying uncensored model.
Setup guide
- 1
Get your key
Sign up with Google or email to receive your API key instantly.
- 2
Set base URL
Point your client library to HTTPS://api.claudeapiproxy.com/v1 and set the key.
- 3
Send requests
Call the API with model id "uncensored" and start generating text.
Common use cases
Uncensored coding
Pair proxy tools with coding models for unrestricted code generation sessions.
NSFW chatbots
Deploy adult chat applications without content refusal filtering on lawful topics.
Research agents
Run autonomous agents that explore controversial or sensitive topics freely.
Local model proxy
Route existing OpenAI SDK calls to our server for transparent billing.
Moving from another OpenAI-compatible provider in three steps
Switching is immediate. Update your base URL to HTTPS://api.claudeapiproxy.com/v1 and replace the API key. Send requests to the "uncensored" model using standard OpenAI SDKs. No code changes are required for chat completions. Streaming, tools, and JSON modes work identically. Start with $0.50 trial credit to verify latency and token accuracy before topping up via crypto.
Who uses it, in which real situations; and plainly who it is NOT for
Developers building NSFW chatbots, adult content generators, and coding assistants using standard OpenAI SDKs deploy this uncensored LLM API for unrestricted lawful text generation.
- Content creators avoiding arbitrary refusals.
- Code agents rerouting calls via proxy tools.
It is NOT for teams needing image generation, embeddings, or multi-model routing. Use this only when you require a single, dedicated uncensored model via a compatible interface.
claude API proxy: uncensored chat-completions for adults and coders
The claude API proxy delivers a single, uncensored large language model via a standard OpenAI-compatible interface, eliminating content restrictions for lawful adult use and coding tasks.
NSFW creative writing
Generate unrestricted stories without unexpected refusals. The model handles controversial topics directly.
Code generation
Use the API with existing client code. Send requests to the chat-completions endpoint.
Developer integration
Connect via the base URL. Adjust the API key in your SDK configuration.
A checklist for choosing a provider in this niche
Verify uncensored constraints and model identity
- Confirm the model ID is explicit, not a routed alias.
- Check if adult content is allowed without hidden filters.
Ensure the API follows OpenAI standards for easy switching. Verify prepaid token billing matches your usage pattern. Avoid providers with hidden monthly fees or complex tier structures. Test streaming support for real-time needs. Confirm no data training on your prompts.
Common mistakes people make in this niche and how to avoid them
Common mistakes people make in this niche and how to avoid them
- Assuming all proxy APIs support function calling. We do, but many others do not.
- Ignoring context window limits. Our model handles 100,000 tokens total, not just input.
- Forgetting rate limits. We cap requests at 300 per minute per key to ensure stability.
Worked cost examples with token arithmetic that use only our prices
Your bill reflects real token usage, not subscriptions. Each request incurs input costs at $0.15 per million tokens plus output costs at $0.50 per million tokens. Errors remain free. Consider a 20,000 token prompt generating 2,000 tokens. Input charges $0.003. Output charges $0.001. Total cost equals $0.004. Prepaid credit never expires. You pay only for what you consume.
Frequently asked questions
What is claude API proxy and how does it work?
It is an independent service rerouting requests to our uncensored model. You swap the base URL and API key. The interface remains OpenAI-compatible. This eliminates vendor lock-in. Your existing client code works immediately without modification for chat completions.
Does the uncensored model refuse adult content?
No. It answers without refusals for lawful adult, fictional, or controversial topics. Only sexual content involving minors is strictly refused. This ensures reliable generation for NSFW chatbot use cases. You retain full control over the output content via standard parameters.
What payment methods are accepted for topping up credit?
We accept only USDT on TRC20 or USDC on Base. Any whole amount from twenty to five hundred dollars qualifies. Plus five percent bonus credit applies from fifty dollars.
Are there any monthly subscription fees or hidden costs?
No. You pay only for real tokens consumed. Errors and refusals are free. There are no monthly fees. Paid credit never expires. This transparent prepaid model ensures you only fund actual usage without worrying about recurring charges or hidden service fees.
Can I use the official OpenAI SDK with this proxy?
Yes. The API is fully OpenAI-compatible. You simply update the base URL and API key in your configuration. Streaming via SSE, function calling, and JSON mode all work natively. Your existing Python or Node.js code requires no structural changes to function.
How much does the uncensored LLM API cost per token?
Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. These rates apply to real usage only. Errors do not incur charges. This pricing structure allows precise cost tracking for high-volume coding projects or NSFW chatbot applications efficiently.
Get your API key now
Sign up, copy the key, update your base URL. That is the entire configuration.
Get API key$0.50
trial credit