API Quickstart Guide

Authentication & Base URL

Set your base URL to https://api.deepseekuncensored.com/v1 and pass your API key in the Authorization header. You retrieve this key immediately after signing up with Google or your email. The system enforces a strict limit of one active key per account, so generating a new key automatically revokes the previous one. Keep this key secure because it grants full access to your prepaid credit.

Chat Completions Endpoint

Send standard JSON payloads to POST /v1/chat/completions to receive text responses. The endpoint accepts your model ID as uncensored and supports parameters like temperature and top_p. You can configure a context window of 100,000 tokens for both prompt and completion. Ensure your request body stays under 8 MB to avoid truncation or rejection.

Copycurl https://api.deepseekuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Streaming Responses (SSE)

Enable real-time token output by setting stream: true in your request. The server returns Server-Sent Events (SSE) that you can parse incrementally. Token usage statistics appear in the final chunk of the stream. This approach reduces perceived latency for long-form content generation tasks.

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)

Function Calling & JSON Mode

Utilize the tools and tool_choice parameters to enable function calling capabilities. You can also enforce strict JSON output using response_format set to json_object. These features allow you to integrate the LLM directly into structured data pipelines. The model returns raw text, so you handle the parsing logic in your client code.

Copyfrom openai import OpenAI

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

Rate Limits & Quotas

Each API key supports 300 requests per minute and a concurrency limit of eight simultaneous requests. If you exceed these thresholds, the server returns a 429 error. You can monitor your usage and top up your balance via the dashboard. Prepaid credit never expires, so you can pause usage without losing funds.

Error Handling

Handle standard HTTP errors like 401 for invalid keys and 402 when your balance is insufficient. A 429 status indicates you have hit the rate limit. Errors do not consume your prepaid credit, so failed requests are free. Always check the response body for detailed error messages to debug payload issues quickly.

Copyimport OpenAI from "openai";

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