API key deepseek: openai-compatible quickstart

Base URL and authentication

The base URL for all requests is HTTPS://api.apikeydeepseek.com/v1. You authenticate by passing your unique API key in the Authorization header. This key is generated instantly upon signup via Google or email, with no phone number required. Use the same OpenAI-compatible client libraries you already know; just update the base URL and key.

First request

Send a POST request to /v1/chat/completions with the model ID uncensored. The model responds to prompts without refusing lawful adult or controversial topics. Errors and refusals do not consume your prepaid credit.

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

Python SDK

Configure the OpenAI Python client with the custom base URL and your key. Set the model to uncensored to access the open-weight model running on our servers. You can adjust temperature and top_p to control creativity. The client handles token counting automatically.

Copyfrom openai import OpenAI

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

Node SDK

Initialize the OpenAI Node.js client with the same base URL. Pass uncensored as the model name. You can enable streaming or JSON mode directly in the request. The SDK manages the connection lifecycle and error handling for you.

Copyimport OpenAI from "openai";

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

Streaming responses with SSE

Enable streaming by setting stream: true. The API returns Server-Sent Events (SSE). Token usage data appears in the final chunk. This is ideal for real-time chat interfaces or roleplay applications. You process each chunk as it arrives.

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)

Rate limits and concurrency

Each API key supports 300 requests per minute and 8 concurrent requests. The maximum request body is 8 MB. The context window is 100,000 tokens for prompt and completion combined. A 401 error means an invalid key. A 402 error indicates insufficient credit. A 429 error means you hit the rate limit.