クイックスタート：Uncensored API統合

Python SDK Integration

Use the official Python library to interact with the API programmatically. Initialize the client with your base URL and API key. This setup ensures compatibility with existing codebases.

Pass your messages array to the chat.completions.create method. The response contains the generated text and token usage. Errors are raised as standard exceptions. Check your balance before heavy usage.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.apikeyforclaudecode.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 Implementation

Integrate the API into Node.js applications with minimal code changes. Set the baseUrl to our endpoint. Pass your API key as the apiKey value.

Create a completion request with your system and user messages. Handle the response object to extract the content. This method supports JSON mode and function calling for structured outputs.

Copyimport OpenAI from "openai";

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

Handling Streaming Responses

Enable streaming for lower latency and real-time token display. Set the stream parameter to true in your request. The API returns a server-sent events (SSE) stream.

Parse each chunk to access partial completions. The final chunk includes total token usage. This feature is essential for chat interfaces and live coding tools.

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, Errors, and Context

Understand the operational limits to optimize your application. The context window supports 100,000 tokens total. Max output is 16,000 tokens per request. Errors like 401 indicate invalid keys. 402 errors mean no credit. 429 signals rate limits. Your prepaid credit never expires.