Uncensored chat completions docs

Authentication & Base URL

The base URL is HTTPS://api.pricingapiopen.com/v1. Pass your API key in the Authorization header. We use the standard Bearer scheme. You receive one key immediately after signup. Use the key in every request to identify your account and deduct credit.

Chat Completions Endpoint

Send messages to POST /v1/chat/completions. Include your model id as uncensored. Provide the system, user, and assistant roles in the messages array. The API returns a text response. You can set temperature and top_p to control randomness.

• Set model to uncensored.
• Include a user message with your prompt.

Copycurl https://api.pricingapiopen.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate total monthly cost for 1 million tokens"}]
  }'

Uncensored Model Parameters

The model accepts standard generation parameters. Use temperature for creativity. Set top_p for nucleus sampling. You can define stop sequences to halt generation early. Pass a seed for reproducible outputs. The model does not refuse lawful adult content. It answers directly without extra fluff.

Streaming & Token Usage

Enable streaming by setting stream to true. The API returns chunks of text as they are generated. You receive token usage data in the final chunk. This helps you track costs in real time. Streaming reduces perceived latency for users.

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)

Python & Node SDKs

Use the official OpenAI Python SDK. Set the base URL to our endpoint. The code works exactly like the standard library. You can also use the Node.js SDK. Change the base URL in the configuration object. Both SDKs handle authentication automatically.

Copyfrom openai import OpenAI

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

For JavaScript developers, the Node SDK works with our endpoint. Configure the base URL and API key. Send requests using the chat.completions.create method. The response structure matches the OpenAI format.

Copyimport OpenAI from "openai";

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

Limits, Errors & Context

You have a 100,000 token context window. The max output is 16,000 tokens per request. You can send 300 requests per minute. Errors return standard HTTP codes. A 401 error means your key is invalid. A 402 error means you need more credit. A 429 error means you hit the rate limit.