API 调用示例#

示例默认使用环境变量：

export OMG_API_KEY="sk-你的API令牌"
export OMG_BASE_URL="https://api.omgrouter.cc"

bash

获取模型列表#

curl "$OMG_BASE_URL/v1/models" \
  -H "Authorization: Bearer $OMG_API_KEY"

bash

Chat Completions#

适合 OpenAI 兼容聊天接口。

curl "$OMG_BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $OMG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-mini",
    "messages": [
      { "role": "system", "content": "你是一个简洁的助手。" },
      { "role": "user", "content": "只回复 OK" }
    ],
    "max_tokens": 8
  }'

bash

文本读取位置：

choices[0].message.content

text

Responses API#

适合 GPT 系列新项目和 Codex 类客户端。

curl "$OMG_BASE_URL/v1/responses" \
  -H "Authorization: Bearer $OMG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-mini",
    "instructions": "你是一个简洁的助手。",
    "input": "只回复 OK",
    "max_output_tokens": 8
  }'

bash

当前服务端可能不会填充 output_text 快捷字段，建议使用兼容读取方式：

function getResponseText(response) {
  if (typeof response.output_text === "string" && response.output_text) {
    return response.output_text;
  }

  return (response.output || [])
    .flatMap((item) => item.content || [])
    .filter((part) => part.type === "output_text" && part.text)
    .map((part) => part.text)
    .join("");
}

Python 标准库示例#

无需安装 SDK，适合排查网络和鉴权问题。

import json
import os
import urllib.request

api_key = os.environ["OMG_API_KEY"]
base_url = os.environ.get("OMG_BASE_URL", "https://api.omgrouter.cc")

payload = {
    "model": "gpt-5.4-mini",
    "messages": [{"role": "user", "content": "只回复 OK"}],
    "max_tokens": 8,
}

request = urllib.request.Request(
    f"{base_url}/v1/chat/completions",
    data=json.dumps(payload).encode("utf-8"),
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    method="POST",
)

with urllib.request.urlopen(request, timeout=60) as response:
    data = json.loads(response.read().decode("utf-8"))

print(data["choices"][0]["message"]["content"])

python

Node 原生 fetch 示例#

Node.js 18+ 可直接运行。

const apiKey = process.env.OMG_API_KEY;
const baseUrl = process.env.OMG_BASE_URL || "https://api.omgrouter.cc";

const response = await fetch(`${baseUrl}/v1/chat/completions`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gpt-5.4-mini",
    messages: [{ role: "user", content: "只回复 OK" }],
    max_tokens: 8,
  }),
});

if (!response.ok) {
  throw new Error(`${response.status} ${await response.text()}`);
}

const data = await response.json();
console.log(data.choices[0].message.content);

OpenAI Python SDK#

pip install openai

bash

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的API令牌",
    base_url="https://api.omgrouter.cc/v1",
)

response = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[{"role": "user", "content": "只回复 OK"}],
    max_tokens=8,
)

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

python

OpenAI Node SDK#

npm install openai

bash

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OMG_API_KEY,
  baseURL: "https://api.omgrouter.cc/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-5.4-mini",
  messages: [{ role: "user", content: "只回复 OK" }],
  max_tokens: 8,
});

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

Claude Messages#

适合 Claude 官方协议。令牌分组请使用 CC 或 CC-N，具体见模型分组。

curl "$OMG_BASE_URL/v1/messages" \
  -H "Authorization: Bearer $OMG_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4.5",
    "max_tokens": 64,
    "messages": [
      { "role": "user", "content": "只回复 OK" }
    ]
  }'

bash

Embeddings#

curl "$OMG_BASE_URL/v1/embeddings" \
  -H "Authorization: Bearer $OMG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "OMG Router 文档测试"
  }'

bash

Gemini 兼容生成#

curl "$OMG_BASE_URL/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Authorization: Bearer $OMG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{ "text": "只回复 OK" }]
      }
    ]
  }'

bash

如果返回模型不存在，请先在控制台确认当前令牌分组是否包含该 Gemini 模型。

账户令牌用量#

令牌维度的用量接口：

curl "$OMG_BASE_URL/api/usage/token/" \
  -H "Authorization: Bearer $OMG_API_KEY"

bash

该接口会返回令牌名称、已用额度、剩余额度、模型限制、过期时间等信息。