API Quickstart Guide

Base URL and Authentication

Connect your existing OpenAI SDK by updating the base URL and providing your API key. Our service sits at https://api.deepseekapidiscount.com/v1 and accepts the standard Authorization: Bearer header. Your key works immediately after creation, granting access to the uncensored model without monthly subscriptions. This setup lets you swap in our endpoint while keeping your application code identical to OpenAI standards.

The authentication flow is straightforward. You generate a key on our dashboard and pass it as a header. Errors like 401 indicate an invalid key, while 402 means your prepaid credit is exhausted. You can top up via USDT or USDC at any time, and your credit never expires. This prepaid model ensures you only pay for the tokens you actually use, with no hidden fees or tier limits.

Chat Completions Endpoint

Send your first request to the /v1/chat/completions endpoint using the model ID uncensored. This endpoint handles text-in, text-out interactions without any built-in content moderation. You can control the response style using parameters like temperature and top_p. The model supports a context window of 100,000 tokens, allowing for extensive conversation history or document processing in a single call. Max output is capped at 16,000 tokens per request, or 2,048 if you omit the limit.

• Use response_format with json_object for structured data output.
• Set stream: true for real-time token delivery.
• Pass stop sequences to halt generation at specific markers.

This endpoint is the core of our API, designed for developers who need raw, unfiltered model outputs. It does not offer embeddings or image generation, keeping the service focused and cost-effective. You pay $0.15 per million input tokens and $0.50 per million output tokens. Errors do not consume your credit, so you can test freely without worrying about wasted funds.

Streaming and Token Usage

Enable streaming by setting stream: true in your request body. The API returns Server-Sent Events (SSE) with each generated token. The final chunk in the stream contains the full token usage statistics for the request. This allows you to monitor costs in real-time as the model generates text. Streaming is ideal for chat interfaces where users expect instant feedback.

The token usage object includes input tokens, output tokens, and sometimes total tokens. Since our API is prepaid, you can track your remaining credit against these usage numbers. Errors during streaming do not charge you for the tokens already sent. This transparency helps you manage your budget effectively, especially when running long conversations or processing large documents. The 100,000-token context window supports deep historical context without truncation.

Function Calling and JSON Mode

Use function calling to integrate our API into agent workflows. Define your tools in the tools parameter and set tool_choice to auto or a specific function ID. The model will return a tool call object if the input requires external action. This feature works alongside JSON mode, which forces the output into a strict JSON schema using response_format. You can combine these for robust structured data extraction.

Function calling supports multiple tools in a single request. The model decides which tool to use based on the input context. JSON mode is useful when you need predictable data structures for downstream processing. Both features are available at the same base price of $0.15 per million input tokens. This flexibility makes our API suitable for complex applications requiring precise output formatting.

Limits and Best Practices

Each API key is limited to 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. These limits ensure fair usage and stable performance for all users. If you exceed the rate limit, you will receive a 429 error. You can create a new key to replace an old one if needed, but only one key is active per account. This simplicity reduces management overhead for small teams.

Best practices include setting a max_tokens limit to control costs and avoid infinite generation. Use stop sequences to prevent the model from rambling. Monitor your token usage via the streaming endpoint to stay within your prepaid credit. Since credit never expires, you can top up whenever convenient. The uncensored model does not refuse lawful adult content, but it will block sexual content involving minors. This hard limit applies regardless of your account tier.

Client Examples

Here are code snippets for popular languages. Use the official OpenAI SDKs or any compatible client. Replace YOUR_API_KEY with your generated key. The base URL is https://api.deepseekapidiscount.com/v1. These examples demonstrate basic text generation and streaming. You can adapt them to your specific use case, whether it is chat, summarization, or data extraction.

cURL

Copycurl https://api.deepseekapidiscount.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check server status for uptime reliability and latency metrics"}]
  }'

Python

Copyfrom openai import OpenAI

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