API Reference and Quickstart

Authentication and Base URL

Generate your credential on the dashboard and point your client at the base URL. The endpoint accepts standard OpenAI headers, so you can swap in your key without changing library code. This cheap LLM API works with any tool that reads the AUTHORIZATION header.

Your key is visible immediately after signup. Keep it secure, as it represents your prepaid balance. Errors and refusals do not consume credit, so you can test safely.

First Request

Send a simple chat completion to verify connectivity and receive an uncensored response. The model id is always uncensored for all requests.

• Base URL: https://api.keyapicodeclaude.com/v1
• Method: POST
• Model: uncensored

  Adjust the temperature to control creativity or set max_tokens to cap output length.

  Copycurl https://api.keyapicodeclaude.com/v1/chat/completions \
    -H "Authorization: Bearer $API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "uncensored",
      "messages": [{"role": "user", "content": "Set the max tokens to five hundred"}]
    }'

  Python SDK Integration

  Use the official library to interact with the endpoint programmatically. Set the base URL and API key in the client initialization. This approach works for batch processing or complex agent workflows.

  The library handles retries and JSON serialization automatically. You can access usage data from the response object for billing transparency.

  Copyfrom openai import OpenAI
  
  client = OpenAI(base_url="https://api.keyapicodeclaude.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 Setup

  Initialize the client with your credentials and base URL. The Node SDK mirrors the Python behavior, making it easy to switch languages or run in serverless environments.

  Pass the message history as an array of objects. The API returns a structured response containing the generated text and token counts. Error handling is standard across all SDKs.

  Copyimport OpenAI from "openai";
  
  const client = new OpenAI({ baseURL: "https://api.keyapicodeclaude.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

  Enable streaming by setting stream: true in your request. The server sends Server-Sent Events (SSE) containing partial tokens. This reduces perceived latency for interactive applications.

  Parse the chunks to build the full response incrementally. The final chunk includes token usage statistics for billing verification. Streaming is essential for real-time user experiences.

  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)

  Limits and Errors

  Monitor your usage to avoid service interruptions. The context window supports 100,000 tokens for prompt and completion combined. Max output is 16,000 tokens per request, or 2,048 if unspecified.

  Rate limits enforce 300 requests per minute and 8 concurrent requests per key. Common errors include 401 for invalid keys, 402 for insufficient credit, and 429 for rate limits. Request bodies must stay under 8 MB.