API Documentation for Developers

Base URL and authentication

Set your base URL to https://api.deepseekabliterated.com/v1 and pass your key in the Authorization header. The API requires no proxy configuration and works directly with standard OpenAI SDKs. Create an account via Google or email on the Get API key page to receive your credentials instantly. No phone number is required for signup, and the key is displayed immediately after creation. You may have only one active key per account; generating a new one replaces the old key. Use the Authorization: Bearer YOUR_API_KEY header for all requests. Errors and refusals do not consume tokens, so you can test safely.

First request with curl

Send a POST request to /v1/chat/completions with the model ID set to uncensored. The endpoint accepts standard JSON payloads and returns text responses. Use this command to verify your key and see the model in action immediately.

Copycurl https://api.deepseekabliterated.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list available model endpoints for local deployment"}]
  }'

This request demonstrates the basic text-in, text-out functionality. The API supports up to 100,000 tokens for the combined prompt and completion. Max output is 16,000 tokens per request, or 2,048 if max_tokens is unset. Streaming is available via Server-Sent Events for real-time token delivery.

Python SDK integration

Install the OpenAI Python package and configure the base URL to point to our service. This allows you to use existing code without modifications. The SDK handles authentication and request formatting automatically. Pass your API key as an environment variable or directly in the client initialization. This approach works for any OpenAI-compatible client, not just the official SDK. You can use function calling, JSON mode, and standard parameters like temperature and top_p. The model responds to tool definitions and returns structured JSON when requested.

Copyfrom openai import OpenAI

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

This setup ensures compatibility with your current workflow. The API does not support embeddings, images, or fine-tuning, so stick to chat completions. Token usage is billed per 1M tokens, with input at $0.15 and output at $0.50. Prepaid crypto credits never expire, so you can pause usage without losing funds.

Node SDK integration

Use the OpenAI Node.js SDK to integrate the uncensored model into your JavaScript or TypeScript applications. Set the baseURL to https://api.deepseekabliterated.com/v1 and provide your API key. This method mirrors the Python setup, ensuring consistency across your tech stack. The SDK supports streaming responses, which deliver tokens as they are generated. This reduces perceived latency for long outputs. You can handle errors like 401 (invalid key) or 402 (no credit) with standard retry logic. The API limits requests to 300 per minute per key, with a concurrency limit of 8 simultaneous requests. Adjust your implementation to respect these limits. Request bodies must not exceed 8 MB. These constraints apply to all keys and accounts.

Copyimport OpenAI from "openai";

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

Node developers benefit from the same token billing and crypto top-up options. Use USDT on TRC20 or USDC on Base for top-ups, with bonus credit for larger amounts.

Streaming and token usage

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) with incremental token updates. Each chunk contains the generated text, and the final chunk includes token usage details. This allows you to display output in real time without waiting for the full response. Streaming works with all parameters, including function calling and JSON mode. Use the stop parameter to control output length or trigger conditions. The API supports temperature, top_p, seed, presence_penalty, and frequency_penalty for fine-tuning generation. Token usage is reported in the last chunk, so you can track costs accurately. Errors do not consume tokens, even during 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)

This approach is ideal for chat interfaces and long-form content generation. The 100,000 token context window supports extensive conversations or large codebases. Output is limited to 16,000 tokens per request, ensuring predictable latency. For longer outputs, split your requests or use chunking strategies.

Limits, errors, and context window

The API enforces a 300 requests per minute limit per key, with a maximum of 8 concurrent requests. Request bodies must not exceed 8 MB. Errors like 401 (invalid key) or 402 (insufficient credit) do not consume tokens. Rate limits (429) indicate you have exceeded the quota; wait and retry. The context window supports 100,000 tokens for prompt and completion combined. Max output is 16,000 tokens, or 2,048 if max_tokens is not set. The model refuses sexual content involving minors, but allows other lawful adult content. Privacy is maintained; prompts are not used for training. Account creation requires only an email. Credit is prepaid and never expires. Refunds are not issued, but errors like double charges are fixed via Support. Top-ups are crypto-only, with bonuses for larger amounts.