API Documentation

Authentication and Base URL

Your API key authenticates every request to our infrastructure. Use the base URL https://api.deepseeksemfiltro.com/v1 and pass your key in the Authorization header. You can generate this key instantly via Google or email on the dashboard. No phone number is required. The key is displayed immediately after signup.

First Request

Send a standard chat completion request to test connectivity. Replace YOUR_API_KEY with your actual key. The model identifier is uncensored. This endpoint accepts text input and returns text output without content filters for lawful adult use.

Copycurl https://api.deepseeksemfiltro.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show me the latest stable release notes for the core library"}]
  }'

This request demonstrates the basic structure. The response includes token usage and the generated text. Errors return standard HTTP status codes.

Python SDK Integration

Use the official OpenAI Python library for easy integration. Set the base URL and API key in your client configuration. This allows you to use familiar methods like chat.completions.create(). The library handles serialization and streaming automatically.

Copyfrom openai import OpenAI

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

Ensure your library version supports the base URL override. This approach works with any OpenAI-compatible SDK. You can adjust parameters like temperature and top_p directly in the call.

Node.js SDK Usage

Initialize the client with your base URL and key. The Node.js SDK follows the same pattern as the Python version. Pass the model ID uncensored and your message array. This setup works with existing OpenAI codebases.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.deepseeksemfiltro.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 object to access the generated content. The SDK manages the HTTP connection. You can stream responses or get the full text at once. Adjust timeout settings if needed for long contexts.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE). Each chunk contains partial text and token usage data in the final chunk. This reduces perceived latency for users.

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)

Process each chunk as it arrives. Accumulate the text to form the complete response. Error chunks are also streamed. This method is ideal for chat interfaces. The server closes the stream when complete.

Limits and Errors

Your API key is limited to 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. If your key is invalid, you receive a 401 error. A 402 error indicates insufficient credit. A 429 error means you hit the rate limit. The context window is 100,000 tokens total. Errors and refusals do not consume credit. Pricing is $0.15 per 1M input tokens and $0.50 per 1M output tokens.