首次 API 调用

curl -N "$OMNIRELAY_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $OMNIRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-6-luna","messages":[{"role":"user","content":"你好 OmniRelay"}],"max_completion_tokens":1024,"stream":true,"stream_options":{"include_usage":true}}'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["OMNIRELAY_API_KEY"],
    base_url=os.environ["OMNIRELAY_BASE_URL"],
    max_retries=0,
)
stream = client.chat.completions.create(
    model="gpt-6-luna",
    messages=[{"role": "user", "content": "你好 OmniRelay"}],
    max_completion_tokens=1024,
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
    # 用量和费用在最后一个没有 choices 的分块里。
    if chunk.usage:
        print("\n", chunk.usage, getattr(chunk, "cost_microusd", None))

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OMNIRELAY_API_KEY,
  baseURL: process.env.OMNIRELAY_BASE_URL,
  maxRetries: 0,
});
const stream = await client.chat.completions.create({
  model: "gpt-6-luna",
  messages: [{ role: "user", content: "你好 OmniRelay" }],
  max_completion_tokens: 1024,
  stream: true,
  stream_options: { include_usage: true },
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
  // 用量和费用在最后一个没有 choices 的分块里。
  if (chunk.usage) console.log("\n", chunk.usage, chunk.cost_microusd);
}