What is the price claude uncensored API?

It is a pay-as-you-go API for an uncensored LLM. Pricing is $0.15 per million input tokens and $0.50 per million output tokens. No monthly subscription is required.

How do I get an API key?

Sign up on the Get API key page using Google or email. Your key is displayed immediately. No phone number is needed. You can replace the key if needed.

Is the model uncensored?

Yes, it does not refuse lawful adult content. It only blocks sexual content involving minors. You can use it for creative, technical, or controversial topics.

Quickstart: uncensored LLM API integration guide

Prerequisites: SDK and API key setup

The base URL for our hosted service is https://api.priceclaude.com/v1. Authentication requires a valid API key passed in the Authorization header. You generate this key immediately after signing up via Google or email on the Get API key page. No phone number is required for signup.

Our API is OpenAI-compatible. You can use any SDK that supports the standard openai package structure. Pass your key as the api_key parameter. Change the base_url to point to our endpoint. This allows you to swap in our uncensored model without rewriting your integration logic.

Making your first chat completion request

Send a POST request to /v1/chat/completions with your system and user messages. The model identifier is strictly uncensored. It is not another vendor's model. It is an open-weight model tuned for direct answers without content refusals for lawful adult use. You can set parameters like temperature and top_p to control creativity.

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors and refusals do not consume credit. You can verify your request works by sending a simple test message. The response will contain the generated text in the content field.

Handling streaming responses (SSE)

Set stream to true in your request to receive Server-Sent Events. This allows you to process tokens as they generate. Streaming reduces perceived latency for large responses. The final chunk contains the total token usage statistics. This helps you track costs in real-time.

Buffer the incoming chunks and concatenate them. Ensure you handle the end-of-stream event correctly. This approach is essential for chat interfaces. It provides a smooth user experience compared to waiting for the full response.

Using tools and JSON mode

Define function schemas in the tools parameter. The model can call these functions if instructed. Use tool_choice to force a specific function. This enables complex workflows. JSON mode is available via response_format: {type: "json_object"}. This ensures structured output for reliable parsing. Use this for data extraction tasks.

Understanding token usage and limits

The context window is 100,000 tokens combined. This includes both the prompt and the completion. The maximum output per request is 16,000 tokens. If you do not set max_tokens, it defaults to 2,048. Request body size is limited to 8 MB. You can make 300 requests per minute. Concurrency is limited to 8 simultaneous requests per key. Exceeding these limits returns a 429 error.

Error handling and retry logic

Handle HTTP 401 by verifying your API key. A 402 error means your prepaid credit is exhausted. Top up via crypto to continue. Use exponential backoff for 429 rate limit errors. Retry logic should respect the Retry-After header if present. Errors do not charge credit. This protects your balance during network issues.

cURL

curl https://api.priceclaude.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summit the quarterly report by Friday at noon"}]
  }'

Python

from openai import OpenAI

client = OpenAI(base_url="https://api.priceclaude.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)

Node.js

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.priceclaude.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);

Streaming

stream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Quickstart: uncensored LLM API