Quickstart

LLMoxy is an OpenAI-compatible LLM aggregation gateway. With a single LLMoxy API Key, you can switch between OpenAI, Claude, Gemini, and other models without applying for or managing separate vendor accounts.

Create an API Key

  1. Sign up and log in at llmoxy.com.
  2. Go to Console → Tokens and click Create.
  3. Copy the generated key, which usually starts with sk-. Keep it safe. If it leaks, disable it immediately on the same page and create a new one.

Base URL

All OpenAI-compatible clients use the same URL:

https://llmoxy.com/v1

Other request formats (Anthropic, Gemini) use subpaths on the same origin. See Compatible formats for details.

Your first request

curl https://llmoxy.com/v1/chat/completions \
  -H "Authorization: Bearer <LLMOXY_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.7",
    "messages": [
      { "role": "user", "content": "Say hello in one short sentence." }
    ]
  }'
BASH

Replace <LLMOXY_API_KEY> with the key you just created. You can look up model names with GET /v1/models, or browse the model list in the console.

OpenAI SDK

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.LLMOXY_API_KEY,
  baseURL: "https://llmoxy.com/v1",
});

const response = await client.chat.completions.create({
  model: "grok-4.7",
  messages: [{ role: "user", content: "Write a haiku about routers." }],
});

console.log(response.choices[0]?.message?.content);
TS
from openai import OpenAI

client = OpenAI(
    api_key="<LLMOXY_API_KEY>",
    base_url="https://llmoxy.com/v1",
)

response = client.chat.completions.create(
    model="grok-4.7",
    messages=[{"role": "user", "content": "Write a haiku about routers."}],
)

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

Streaming

Set stream: true in a Chat Completions request, and LLMoxy returns an OpenAI-compatible SSE stream.

curl https://llmoxy.com/v1/chat/completions \
  -H "Authorization: Bearer <LLMOXY_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.7",
    "stream": true,
    "messages": [
      { "role": "user", "content": "Count from one to five." }
    ]
  }'
BASH

Next steps

  • Use GET /v1/models to see all models available to the current Key.
  • Read Authentication to learn which vendor-style request headers are supported.
  • Read Chat Completions to integrate using that format.