Uncensored API Quickstart

Base URL and Authentication

Start every request to our claude pricing api compatible endpoint by setting the base URL and API key. We use standard OpenAI headers, so you only need to change the base_url and inject your key into the Authorization header. Signup is fast: use Google or an email password to get a key immediately without phone verification. We do not store prompts for training, ensuring your data remains yours. Every account gets one active key that replaces the old one if you generate a new one.

Sending Your First Completion

Send a text-in, text-out request to the chat completions endpoint with the model ID set to uncensored. This is an open-weight model tuned for lawful adult content and lacks the refusals of mainstream providers. You can send up to 8 requests simultaneously per key. Errors and refusals do not consume your prepaid credit. Use the following command to verify connectivity and token consumption.

Copycurl https://api.claudepricingapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "get current api usage stats"}]
  }'

Using the Python SDK

Install the official OpenAI Python library and point it at our base URL to start generating text. This approach works because we are an OpenAI-compatible API that supports standard parameters like temperature and top_p. You can switch from a subscription service to this uncensored AI API without rewriting your core logic. The SDK handles retries and JSON parsing automatically. Here is how to initialize the client and send a simple prompt.

Copyfrom openai import OpenAI

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

Integrating with Node.js

Use the Node.js OpenAI package to integrate this uncensored AI API into your JavaScript or TypeScript projects. Configure the fetch agent to handle our specific network requirements if you encounter proxy issues. This method is ideal for server-side rendering or backend microservices that need reliable text generation. You can pass multiple messages in the history array to maintain context. The following snippet demonstrates a basic completion request.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.claudepricingapi.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 Responses via SSE

Enable streaming by setting stream: true to receive tokens as they are generated via Server-Sent Events. This reduces perceived latency for users waiting for long responses. You can parse the final chunk to get the exact token usage for billing transparency. Streaming is supported for all standard parameters including stop sequences and seed values. Use this approach for real-time chat interfaces or progressive text rendering.

Copystream = 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)

Rate Limits and Constraints

Respect the 300 requests per minute limit and the 8 MB request body size to avoid service interruptions. If you exceed the limit, you will receive a 429 error; if your credit is exhausted, you get a 402 error. Invalid keys trigger a 401 response. The context window supports 100,000 tokens for prompt plus completion combined. Max output is 16,000 tokens per request unless you specify a lower max_tokens value. These constraints ensure fair usage across all prepaid accounts.