控制台

GPT 5.6 Sol 经济版

GPT-5.6 Sol 是 OpenAI GPT-5.6 系列的旗舰模型。它专为复杂推理、编程和智能体工作流而设计，尤其擅长多步骤问题解决、命令行辅助和高质量软件任务。当输出质量和可靠性比原始吞吐量更重要时，推荐使用该模型。

gpt-5.6-sol

1 身份验证

该 API 使用 API Key 进行身份验证。

获取你的 API Key

从 https://icreat.ai/hub/keys 获取你的 API key。

2 调用 API

该模型提供与 OpenAI 的 /chat/completions API 兼容的 HTTP API。你可以使用任何与此 API 兼容的 SDK 来调用该 llm。

2.1 curl

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST https://api.icreat.ai/llm/openai/v1/chat/completions \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-5.6-sol",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Coffee or tea ? Which is healthier? "}
  ],
  "thinking": {"type": "enabled"},
  "reasoning_effort": "low",
  "stream": false
}'

2.2 python

import os
from openai import OpenAI

client = OpenAI(
    api_key="ICREAT_API_KEY",
    base_url="https://api.icreat.ai/llm/openai",
)

completion = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Coffee or tea ? Which is healthier? "}
    ]
)

print(completion.choices[0].message.content)

2.3 node.js

const OpenAI = require("openai");

const client = new OpenAI({
  apiKey: "ICREAT_API_KEY",
  baseURL: "https://api.icreat.ai/llm/openai",
});

async function main() {
  const completion = await client.chat.completions.create({
    model: "gpt-5.6-sol",
    messages: [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Coffee or tea ? Which is healthier? "}
    ]
  });

  console.log(completion.choices[0].message.content);
}

main();

3 API 协议

3.1 流式输出

将 stream 参数设置为 true 以请求流式输出。

{
  "model": "gpt-5.6-sol",
  "messages": [
    {
      "role": "user",
      "content": "Please explain what recursion is and give a Python example."
    }
  ],
  "stream": true
}