API Documentation

Base URL and Authentication

Connect using your API key for immediate access to the uncensored LLM. All requests require a valid bearer token in the Authorization header. We do not charge for failed authentication or model routing errors.

Use the base URL https://api.deepseekapiprices.com/v1 with any standard OpenAI SDK. Your key provides access to the uncensored model. No phone number is required for signup, and the key is shown immediately after you create an account.

Authentication Example

Replace your-api-key with your actual key. The server validates the token before processing your request.

First Request

Send a simple chat completion to test connectivity and response quality. This endpoint returns text in the choices[0].message.content field. We support function calling and JSON mode for structured outputs.

• Model ID: uncensored
• Endpoint: POST /v1/chat/completions
• Max Output: 16,000 tokens

The request below demonstrates a basic prompt. Ensure your API key is correct to avoid a 401 error.

Copycurl https://api.deepseekapiprices.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Translate this technical documentation to German"}]
  }'

Verify the response structure matches the OpenAI standard. This ensures you can switch providers without rewriting your application logic.

Python SDK Integration

Install the official OpenAI package and configure the base URL. This approach works with the standard openai Python library. You only need to adjust the client configuration.

• Base URL: https://api.deepseekapiprices.com/v1
• API Key: Set via environment variable or constructor
• Model: uncensored

The following code snippet shows the minimal setup. It handles the request and prints the content. Errors are raised as standard OpenAI exceptions.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.deepseekapiprices.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 method is ideal for backend services and scripts. It maintains compatibility with existing codebases.

Node SDK Setup

Configure the Node.js client with the custom base URL. This allows you to use the standard openai package. The setup is identical to other OpenAI-compatible services.

• Base URL: https://api.deepseekapiprices.com/v1
• Package: openai (npm)
• Model: uncensored

Use the following code to initialize the client. It ensures all requests are routed correctly. You can then call chat.completions.create as usual.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.deepseekapiprices.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 errors appropriately to manage rate limits or insufficient credits. The SDK throws standard errors for API issues.

Streaming and Token Usage

Enable streaming for real-time token delivery. Set stream: true in your request parameters. The API returns chunks as they are generated. Token usage details appear in the last chunk.

• Streaming: Supported via SSE
• Token Usage: Provided in the final chunk
• Parameters: temperature, top_p, stop

Stream processing reduces perceived latency for long responses. It is essential for chat interfaces. The following example demonstrates the streaming setup.

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)

Parse the stream to update the UI incrementally. This improves the user experience significantly.

Rate Limits and Context Window

Respect the 300 requests per minute limit per key. You can have 8 concurrent requests at the same time. The request body must not exceed 8 MB. Errors and refusals are free, so rate limits only apply to successful requests.

The model supports a 100,000 token context window. This includes both prompt and completion tokens. Use this for long documents or extended conversations. The following table summarizes the limits.

Limit	Value
Requests per minute	300
Concurrent requests	8
Max request body	8 MB
Context window	100,000 tokens

Exceeding these limits returns a 429 error. Increase concurrency carefully to avoid throttling.