快速入门：无审查 AI 用于 编码 API

前提条件与基础 URL

从仪表板获取您的 API 密钥。使用此基础 URL 发起所有请求： https://api.uncensoredaiforcoding.com/v1. 它与任何 OpenAI SDK 兼容。

安装官方 SDK

在您的环境中安装包。这确保了与 uncensored 编码 AI 标准的兼容性。

Copyfrom openai import OpenAI

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

发起首次请求

发送一个简单的补全以测试连接。模型 ID 为 uncensored.

Copycurl https://api.uncensoredaiforcoding.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "get current unix timestamp in python"}]
  }'

启用流式传输以实现实时输出

流式响应以高效处理长代码块。使用 stream flag。

Copyimport OpenAI from "openai";

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

处理错误和使用限制

如果您达到每分钟 300 次请求，预计会出现 429 错误。上下文窗口为 100,000 个 token。最大输出为 16,000 个 token。

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)

使用 JSON 模式进行结构化数据

为您的代码解析器强制结构化输出。设置 response_format 到 {"type": "json_object"}.