What is the context window for uncensored deepseek API requests?

The context window is 100,000 tokens including prompt and completion. Max output is 16,000 tokens per request. Set 2,048 tokens if max_tokens is undefined.

Does the uncensored model filter NSFW content?

The model does not refuse lawful adult, fictional, or controversial topics. It only blocks sexual content involving minors. This applies to all requests regardless of credit balance.

How does billing work for the deepseek unrestricted API?

Credit is charged by real token usage. Errors and refusals are free. You top up with crypto only. Credit never expires and includes bonuses for larger amounts.

API Documentation - deepseek unrestricted

Authentication and base URL setup

Start by obtaining your API key via the dashboard using Google or email. Use the base URL https://api.deepseekunrestricted.com/v1 for all requests. Pass the key in the Authorization header as a bearer token.

curl https://api.deepseekunrestricted.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the current version of the linux kernel"}]
  }'

Your key is active immediately. Rotate it anytime from the dashboard if needed.

First request with Python

Initialize the client with your base URL and key. Set the model ID to uncensored. This model answers without content refusals for lawful adult use.

from openai import OpenAI

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

The response contains the generated text. You can adjust parameters like temperature for creativity. Errors are free, so retry logic is safe.

Node.js integration

Install the official OpenAI SDK or use fetch directly. Configure the base URL to point to our endpoint. Pass the model ID uncensored in the request body.

import OpenAI from "openai";

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

Handle the response stream or parse the JSON object. This approach works with any OpenAI-compatible client library. You only pay for tokens used.

Streaming responses

Enable streaming by setting stream: true. The API returns Server-Sent Events (SSE). Each chunk contains partial text and token usage data.

stream = 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)

Aggregate the chunks to reconstruct the full response. This reduces perceived latency for large outputs. Token counts are accurate per chunk.

JSON mode and tools

Use response_format: {"type": "json_object"} for strict JSON outputs. Enable function calling with the tools parameter. The model supports tool_choice for control.

This ensures reliable parsing for your application logic. Use temperature and top_p to tune randomness. Stop sequences help control output length.

Rate limits and errors

You get 300 requests per minute and 8 concurrent requests per key. A 401 error means your key is invalid. A 402 error indicates insufficient credit.

curl https://api.deepseekunrestricted.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the current version of the linux kernel"}]
  }'

A 429 error signals rate limit exceeded. Requests over 8 MB body size fail. Credit never expires. Refusals are free. Use the support page for billing issues.

API Documentation