How does the uncensored AI API handle content?

The model does not refuse lawful adult, fictional, or controversial topics. It only blocks sexual content involving minors. Responses are direct without standard corporate filtering. This applies to all requests sent to the endpoint.

What happens if I hit the rate limit?

You receive a 429 Too Many Requests error. You can retry after a short delay. The limit is 300 requests per minute per key. Concurrency is restricted to 8 simultaneous connections. Adjust your client logic to handle these constraints gracefully.

Does the uncensored LLM online service store my prompts?

Prompts are not used for training your data. We store minimal data for billing purposes. Your account requires only an email address. No phone number or personal details are necessary for API access. Privacy is maintained by design.

API 文档 | Set It Uncensored

认证与密钥

认证简单且即时。通过 Google 或电子邮件注册后，您将获得单个 API 密钥。将此密钥传递到 Authorization 作为 bearer 令牌。此密钥标识您的预付费余额并强制执行您的请求限制。通过在仪表板上生成新密钥来轮换密钥；旧密钥会立即停止工作。

聊天完成端点

向 /v1/chat/completions 端点。模型 ID 是 uncensored它接受标准的 OpenAI 消息结构并返回原始文本响应。缺少余额的错误返回 402，无效密钥返回 401。使用此端点进行标准的文本生成任务。

curl https://api.setituncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France."}]
  }'

Python SDK

直接使用官方 OpenAI Python 库进行集成。将基础 URL 配置为指向我们的服务器。传递您的 API 密钥和模型 ID。这种方法适用于期望 OpenAI 兼容性的现有客户端代码。调整参数如 temperature 用于控制随机性。通过 stream flag。

from openai import OpenAI

client = OpenAI(base_url="https://api.setituncensored.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

使用 openai 服务器端集成的 Node.js 包。设置 baseURL 指向我们的 API 端点。使用您的 API 密钥初始化客户端。发送消息并处理响应对象。此设置使您能够轻松地将无审查生成嵌入到 Node 应用程序中。以编程方式管理令牌并处理错误。

import OpenAI from "openai";

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

流式响应

通过将 stream: true 在请求中。你会收到服务器发送事件（SSE）数据块。每个数据块包含部分文本 token。最后一个数据块包含用于 token 计数的使用统计信息。此方法降低了长响应的感知延迟。它非常适合 Web 应用中的实时 UI 更新。

stream = 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)

限制、错误 & 上下文

上下文窗口支持总计 100,000 个 token。每次请求的最大输出为 16,000 个 token。您每分钟限制为 300 次请求。每个密钥的并发请求上限为 8 个。超过 8 MB 的请求将被拒绝。通过实现指数退避来处理 429 错误。余额仅按实际 token 使用量收费。

API 文档