---
title: "Deploy vLLM on StackBlaze"
description: "Run the model with vLLM on a GPU machine, then connect it here with its address, password and model name. Your apps get one OpenAI-compatible API with its own key, inside the project at http://vllm/v1 and on a public HTTPS URL. Streaming, JSON output, tool calling and reasoning pass through unchanged, and prompts are not logged."
category: "ai, development, utilities"
url: https://www.stackblaze.com/templates/vllm
---

# Deploy vLLM

Run the model with vLLM on a GPU machine, then connect it here with its address, password and model name. Your apps get one OpenAI-compatible API with its own key, inside the project at http://vllm/v1 and on a public HTTPS URL. Streaming, JSON output, tool calling and reasoning pass through unchanged, and prompts are not logged.

**[Deploy vLLM on StackBlaze](https://dashboard.stackblaze.com/new/template/vllm)**

## This stack

- **vLLM**: Web service

## What you get

- **One address for your apps**: Apps in the project call http://vllm/v1. Code outside the project calls the public HTTPS URL. Both use the OpenAI format, so OpenAI SDKs work by changing the base URL.
- **Its own API key**: Clients use the key generated in API_KEY. The GPU machine’s password stays in this one app and is never handed to clients.
- **A stable model name**: Clients ask for MODEL_ALIAS. Move to another GPU machine and you change MODEL_URL and MODEL_API_KEY only. No client has to change.
- **vLLM features pass through**: Streaming, JSON output (response_format), tool calling and reasoning_content come back exactly as vLLM sends them.
- **No prompt logging**: There is no database and message logging is off, so prompts and answers are not stored by this app.
- **Up while the GPU sleeps**: The health check does not depend on the GPU machine, so the app stays up while the machine is asleep or being replaced.

## After you deploy

1. **Start vLLM on your GPU machine**: Note its HTTP address, its password and the name of the model it serves.
2. **Fill in three variables**: Under Variables, set:
3. **Point your apps at it**: Set each app’s OpenAI settings to:

## How it is wired

- **No GPU in the project**: The model is loaded and served by vLLM on your GPU machine. This app only routes requests, so it needs little CPU and memory.
- **Keys kept apart**: Clients authenticate with API_KEY. Requests without it get 401. Only the gateway knows the GPU machine’s password.
- **Long answers allowed**: REQUEST_TIMEOUT is 600 seconds by default, so long answers from reasoning models are not cut off.
- **Encryption to the GPU**: Clients reach the gateway over HTTPS. Traffic from the gateway to the GPU machine is encrypted only when MODEL_URL starts with https://.

## Configuration

- `MODEL_URL` (required)
- `MODEL_API_KEY` (required)
- `MODEL_NAME` (required)
- `MODEL_ALIAS`
- `API_KEY`
- `REQUEST_TIMEOUT`
- `LITELLM_MODE`
- `LITELLM_TELEMETRY`
- `DO_NOT_TRACK`

## Common questions

### Does this template run the model?

No. It connects a vLLM server you run on a GPU machine. The app itself needs no GPU.

### What do I need from the GPU machine?

Three values: its HTTP address (MODEL_URL), its password (MODEL_API_KEY) and the model name vLLM serves (MODEL_NAME). The password is sent as an Authorization: Bearer header.

### How do my other apps connect?

Set their OpenAI base URL to http://vllm/v1, their API key to API_KEY and the model to MODEL_ALIAS. From outside the project, use the app’s public URL followed by /v1.

### Is reasoning kept apart from the answer?

Yes, when vLLM runs with a reasoning parser (for example --reasoning-parser qwen3). The thinking comes back in reasoning_content, in normal and streamed replies.

### Are prompts logged?

Not by this app: it has no database and message logging is off. What the GPU machine logs depends on how vLLM is run there.

### What happens when I replace the GPU machine?

Update MODEL_URL and MODEL_API_KEY, and MODEL_NAME if the model changed, then save. Clients keep the same URL, key and model name.

### What does it cost?

On StackBlaze you pay for the small amount of compute and memory the gateway uses. The GPU machine is billed by whoever runs it.


Source: https://github.com/vllm-project/vllm
