Back to blog

Getting Started with LLM Gateway in 5 Minutes

A step-by-step guide to making your first LLM API request through LLM Gateway — from signup to seeing results in your dashboard.

Getting Started with LLM Gateway in 5 Minutes

This guide walks you through making your first LLM request through LLM Gateway. By the end, you'll have a working API key and a completed request visible in your dashboard.

Step 1: Get an API Key

  1. Sign in to the dashboard.
  2. Create a new Project.
  3. Copy the API key.
  4. Export it in your shell or add it to a .env file:
1export LLM_GATEWAY_API_KEY="llmgtwy_XXXXXXXXXXXXXXXX"

Step 2: Make Your First Request

LLM Gateway uses an OpenAI-compatible API. Point your requests to https://api.llmgateway.io/v1 and you're done.

Using curl

1curl -X POST https://api.llmgateway.io/v1/chat/completions \
2  -H "Content-Type: application/json" \
3  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
4  -d '{
5    "model": "gpt-4o",
6    "messages": [
7      {"role": "user", "content": "What is an LLM gateway?"}
8    ]
9  }'

Using Node.js (OpenAI SDK)

1import OpenAI from "openai";
2

3const client = new OpenAI({
4  baseURL: "https://api.llmgateway.io/v1",
5  apiKey: process.env.LLM_GATEWAY_API_KEY,
6});
7

8const response = await client.chat.completions.create({
9  model: "gpt-4o",
10  messages: [{ role: "user", content: "What is an LLM gateway?" }],
11});
12

13console.log(response.choices[0].message.content);

Using Python

1import requests
2import os
3

4response = requests.post(
5    "https://api.llmgateway.io/v1/chat/completions",
6    headers={
7        "Content-Type": "application/json",
8        "Authorization": f"Bearer {os.getenv('LLM_GATEWAY_API_KEY')}",
9    },
10    json={
11        "model": "gpt-4o",
12        "messages": [
13            {"role": "user", "content": "What is an LLM gateway?"}
14        ],
15    },
16)
17

18response.raise_for_status()
19print(response.json()["choices"][0]["message"]["content"])

Using the AI SDK

If you're using the Vercel AI SDK, you can use our native provider:

1import { llmgateway } from "@llmgateway/ai-sdk-provider";
2import { generateText } from "ai";
3

4const { text } = await generateText({
5  model: llmgateway("openai/gpt-4o"),
6  prompt: "What is an LLM gateway?",
7});

Or use the OpenAI-compatible adapter:

1import { createOpenAI } from "@ai-sdk/openai";
2

3const llmgateway = createOpenAI({
4  baseURL: "https://api.llmgateway.io/v1",
5  apiKey: process.env.LLM_GATEWAY_API_KEY!,
6});

Step 3: Enable Streaming

Pass stream: true to any request and the gateway will proxy the event stream unchanged:

1curl -X POST https://api.llmgateway.io/v1/chat/completions \
2  -H "Content-Type: application/json" \
3  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
4  -d '{
5    "model": "gpt-4o",
6    "stream": true,
7    "messages": [
8      {"role": "user", "content": "Write a short poem about APIs"}
9    ]
10  }'

Step 4: Monitor in the Dashboard

Every call appears in the dashboard with latency, cost, and provider breakdown. Go back to your project to see your request logged with the model used, token counts, cost, and response time.

Step 5: Try a Different Provider

The best part of using a gateway: switching providers is a one-line change. Try the same request with a different model:

1# Anthropic
2"model": "anthropic/claude-haiku-4-5"
3

4# Google
5"model": "google-ai-studio/gemini-2.5-flash"

Same API, same code. Just a different model string.

What's Next

Get started now