Quickstart: uncensored chat completions

Install the openai-compatible client

Choose the SDK that matches your development environment. The API follows standard OpenAI conventions, so you can use any compatible library to send requests.

• Python developers should install the openai package.
• Node.js users need the openai npm package.
• Other languages can use the official SDKs or standard HTTP libraries.

This approach ensures broad compatibility with existing tools and simplifies integration into your projects.

Configure base URL and API key

Set your API key and the custom base URL in your client configuration. This directs requests to our servers instead of the standard OpenAI endpoints.

Configuration

Use the key generated from your dashboard and point to https://api.priceapiseekdeep.com/v1. This setup works with any OpenAI-compatible client by changing the base_url and api_key parameters.

Your prompts are processed without content refusals, making it ideal for creative writing and coding tasks.

Make your first request

Send a standard chat completion request to test the connection. Use the model ID uncensored to access the tuned model.

• Set the model parameter to uncensored.
• Include your system and user messages in the messages array.
• The API returns text output directly.

This confirms your key works and credits are deducted correctly for input tokens.

Enable streaming for real-time output

Activate streaming by setting stream: true in your request. The API returns tokens sequentially as they are generated, improving perceived latency.

• Read tokens from the server-sent events stream.
• The final chunk contains total token usage statistics.
• This method is ideal for chat interfaces and real-time applications.

Streaming reduces wait time for users while the model processes your prompt.

Use function calling and JSON mode

Leverage structured outputs for programmatic interactions. Enable JSON mode by setting response_format to {"type": "json_object"} for consistent parsing.

• Define tools in the tools parameter.
• Set tool_choice to control function invocation.
• Use parameters like temperature and top_p to adjust output randomness.

This feature set supports complex workflows without external parsing logic.

Understand token usage and limits

Monitor your usage to stay within service boundaries. The context window allows 100,000 tokens for prompt and completion combined.

• Maximum output per request is 16,000 tokens.
• Default max output is 2,048 tokens if not specified.
• Rate limit is 300 requests per minute per key.

Premium credits never expire, and errors do not consume your balance. This structure supports high-volume development without monthly subscriptions.

cURL

Copycurl https://api.priceapiseekdeep.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Send 5000 messages to test rate limits"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.priceapiseekdeep.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

Copyimport OpenAI from "openai";

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

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)