vLLM

​

What you’ll need

• ngrok account with AI Gateway access
• vLLM installed
• ngrok agent installed
• GPU with sufficient VRAM for your chosen model
• An access key from app.ngrok.ai

​

Overview

​

Getting started

vllm serve meta-llama/Llama-3.2-8B-Instruct

curl http://localhost:8000/v1/models

ngrok http 8000 --url https://vllm.internal

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.ngrok.ai/v1",
    api_key="ng-xxxxx-g1-xxxxx"
)

response = client.chat.completions.create(
    model="vllm:meta-llama/Llama-3.2-8B-Instruct",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.ngrok.ai/v1",
  apiKey: "ng-xxxxx-g1-xxxxx"
});

const response = await client.chat.completions.create({
  model: "vllm:meta-llama/Llama-3.2-8B-Instruct",
  messages: [{ role: "user", content: "Hello!" }]
});

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

​

Tips

• Secure vLLM: Run with --api-key and attach the key through an access key configuration. The AI Gateway adds it to upstream requests server-side.
• Gated models: Set HF_TOKEN before starting vLLM for Hugging Face gated models.
• Timeouts: Large models can be slow. Increase perRequestTimeout and totalTimeout in account settings.
• Multiple models: Run separate vLLM instances with different internal endpoints and register each as its own custom provider.

​

Troubleshooting

​

Next steps

• Use a model you run yourself: URL requirements and configuration
• Provider Keys: Store upstream credentials
• Quickstart: Create your first access key