Uncensored API integration guide

Prerequisites and model ID

Start by generating your API key via the Get API key page, which supports Google sign-in or email and password. You will send requests to the base URL https://api.apipricing.cc/v1 using the model identifier uncensored. This model supports a 100,000-token context window and does not require embeddings or fine-tuning endpoints.

Authentication with your API key

Pass your key in the Authorization header as a bearer token for every request. The API returns a 401 error if the key is invalid or expired. Your single active key replaces any previous key immediately upon generation, so ensure you update your client configuration when rotating keys.

Sending your first chat completion request

Use a standard POST request to /v1/chat/completions with your system and user messages. The model processes text input and returns text output, supporting JSON mode and function calling. Ensure you include the correct model ID and your API key in the header.

Handling streaming responses and token counts

Enable streaming by setting the stream parameter to true. The API returns server-sent events (SSE) containing partial tokens. You can track token usage by inspecting the final chunk, which includes the total input and output tokens for the request.

Using the Python SDK

Install the official OpenAI package and configure the base URL to point to our service. This allows you to use familiar methods like chat.completions.create without modifying your application logic significantly. The SDK handles the HTTP communication and JSON parsing automatically.

Using the Node SDK and error handling

Initialize the client with your API key and the custom base URL. You will encounter 402 errors if your prepaid credit is exhausted or 429 errors if you exceed 300 requests per minute. Always handle these errors gracefully by checking the response status code and adjusting your retry logic accordingly.

cURL

Copycurl https://api.apipricing.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate total cost for 10 million tokens"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.apipricing.cc/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

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.apipricing.cc/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

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)