Integrate the Codex Key API

Authentication and Base URL

Configure your client with the base URL HTTPS://api.codexkey.cc/v1 and your unique API key. You receive the key immediately after signing up via Google or email, ensuring zero friction. The standard Authorization header expects the format Bearer followed by your string.

• Header: Authorization: Bearer YOUR_API_KEY
• Endpoint: https://api.codexkey.cc/v1

Keep your credentials secure. Each account supports one active key at a time; generating a new one invalidates the previous. This setup works with any standard OpenAI-compatible client library.

Sending Your First Request

Send a POST request to /v1/chat/completions with the model identifier "uncensored". The endpoint accepts standard parameters like temperature and max_tokens. You get direct text responses without extra metadata for simple queries.

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

Use the uncensored model ID to bypass standard content filters. The system processes lawful adult topics, creative writing, and research without refusal. Ensure your payload includes a messages array with your desired prompt structure.

Python SDK Integration

Install the official openai package and point it to our base URL. This approach lets you use familiar Python code to interact with the uncensored LLM. Set the base_url variable to match our endpoint.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.codexkey.cc/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 SDK handles serialization automatically. You can adjust temperature for creativity or top_p for precision. This method is ideal for backend services or local scripts requiring direct text generation.

Node SDK Configuration

Initialize the Node client with the same base URL structure. This allows JavaScript and TypeScript applications to consume the API seamlessly. You can integrate it into web servers or command-line tools.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.codexkey.cc/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 gracefully. The API returns standard HTTP status codes for authentication or rate limit issues. This integration keeps your code clean and compatible with existing Node.js ecosystems.

Streaming Responses via SSE

Enable streaming by setting stream: true in your request. The server sends Server-Sent Events (SSE) token by token. This reduces perceived latency for end-users during long generations.

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)

Token usage statistics appear in the final chunk of the stream. This feature is critical for real-time chat interfaces. You can start displaying text immediately as it arrives, rather than waiting for the full completion.

Limits, Errors, and Context Window

The model supports a 100,000 token context window for combined input and output. Max output per request is 16,000 tokens, or 2,048 if unspecified. Rate limits allow 300 requests per minute per key.

Handle 401 errors by verifying your API key. A 402 error indicates insufficient prepaid credit; top up via crypto to continue. A 429 status means you hit the rate limit; wait briefly before retrying. Errors do not consume credit, ensuring fair usage.