快速开始

几分钟接入：接口与 OpenAI 完全兼容，只需改一个 base_url。

LLM Chat completions

Call leading models like Claude, GPT-4, and DeepSeek via a single OpenAI-compatible API endpoint.

Media generation

Submit asynchronous media generation tasks for image, video, and music models with simple polling.

Prompt caching

Save up to 90% in token pricing on supported models by caching long, static context sequences.

Deep thinking models

Control reasoning effort (low/medium/high) for models like o1/o3 and DeepSeek-R1 natively.

#概览

接口与 OpenAI 完全兼容。用任意 OpenAI SDK 或工具，把 base_url 指向下面的地址、在请求头带上你的密钥，即可调用所有可用模型。

Base URL：https://api.sozdai.ai/v1

#3-Step Quickstart Guide

Get your API key

Create a secure API key in the console to authorize requests. Keep your key confidential.

API Keys

API keys are created inside the **API 密钥 (API Keys)** section. All keys start with `sk-corr-`.

Configure authorization headers

Include the API key in the request headers for authorization:

http

Authorization: Bearer sk-corr-...

Send your first request

Point the API client to the Base URL and invoke the completion endpoint:

curl https://api.sozdai.ai/v1/chat/completions \
  -H "Authorization: Bearer $CORRY_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

#流式输出

设置 stream: true 即可逐 token 接收，格式与 OpenAI 一致，以 data: [DONE] 结尾。

python

resp = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello"}],
    stream=True,
)
for chunk in resp:
    print(chunk.choices[0].delta.content or "", end="")

#支持的参数

请求体与 OpenAI 一致。常用参数如下，其余 OpenAI 字段同样支持：

参数	类型	说明
`stream`	boolean	是否流式返回（SSE）
`max_tokens`	integer	最大生成 token 数
`temperature`	number	采样温度，0–2
`tools`	array	函数调用（tools）
`stop`	string[]	停止序列
`reasoning_effort`	string	开启思考：low / medium / high

#错误码

出错时返回标准错误结构（error 对象含 message 与 type 字段）。常见状态码：

状态码	含义
`401`	密钥无效或缺失
`402`	余额不足，请充值
`404`	请求的模型不存在或不可用
`429`	触发限流，请稍后重试
`502`	服务暂时不可用，请稍后重试