云端大模型与本地模型，一套 API 全部接入

import OpenAI from "openai";

const client = new OpenAI({
  // 替换为你部署的 TokenHub 地址
  baseURL: "http://localhost:8080/v1",
  apiKey: process.env.TOKENHUB_API_KEY,
});
const messages = [{ role: "user", content: "把这段需求整理成任务清单" }];

// 云端与本地模型，调用方式完全一致
for (const model of ["qwen-plus", "ollama/qwen2.5:7b"]) {
  const stream = await client.chat.completions.create({
    model, messages, stream: true,
  });
  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
  }
}

# 地址替换为你部署的 TokenHub 地址
# 云端模型
curl http://localhost:8080/v1/chat/completions \
  -H "Authorization: Bearer $TOKENHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-chat",
       "messages": [{"role": "user", "content": "你好"}]}'

# 本地模型：同一个地址、同一把 Key
curl http://localhost:8080/v1/chat/completions \
  -H "Authorization: Bearer $TOKENHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "ollama/qwen2.5:7b",
       "messages": [{"role": "user", "content": "你好"}]}'