vLLM

Who it is for

For developers and small teams. It runs on Linux, Mac, and a computer you control. License: Apache-2.0. It is in the DevOps group.

What you pay

Free plan: The Apache-2.0 license covers the server. You bring the model weights and the hardware. Hosted price: No vLLM subscription is listed in the README. Someone else hosting a GPU for you is a separate bill. This listing did not check one. Not checked. Run it yourself: Setup: medium. The README's install is uv pip install vllm, then the docs quickstart. It expects a machine with a supported GPU or CPU. This listing did not price that machine.

How to switch

• Compared with Ollama Cloud. Its price on file: Pay as you go is $0 and bills every cloud model per token. Running a model on your own hardware is unlimited. The page does not print when the old free allowance ended.

  You only get part of: a catalog of open models you can pull by name.

  Free alternatives to Ollama Cloud

How close is it?

A full score means it matches our checklist. It is not a drop-in replacement.

• 90
  Instead of Ollama Cloud5 of 5 checked features. A full score means it matches our checklist. It is not a drop-in replacement.You only get part of: a catalog of open models you can pull by name.The README is an install on hardware you operate, including NVIDIA, AMD, Intel, CPUs, and an Apple Silicon plugin.The README says the project includes an OpenAI-compatible API server, plus tool calling.The README says it loads Hugging Face models, including Llama, Qwen, Gemma, and GPT-OSS. Those are architecture names, not the Ollama library tag you pass to ollama run.The server runs where you install it. The README does not describe a vLLM-operated host that stores prompts. This listing did not capture traffic.The README does not list a per-token fee. You pay for the machine and the weights.

Related alternatives

DevOps alternatives

• Free alternatives to Bitbucket
• Free alternatives to Conductor
• Free alternatives to GitHub
• Free alternatives to Jules
• Free alternatives to Ollama Cloud
• Free alternatives to Ona

Free apps in this group

• Aider: Terminal pair programming that commits each edit to git.
• Bugsink: A smaller Sentry-compatible error store.
• Cline: An Apache-2.0 coding agent for VS Code and the terminal. No inline autocomplete.
• Continue: An Apache-2.0 IDE assistant. The repository is read-only after the Cursor acquisition.
• cState: A Hugo status page. Incidents are markdown files.
• Cursor: A coding editor with Tab autocomplete and an agent. Free is limited. The code is closed.
• Devin: The desktop editor formerly sold as Windsurf. Free includes Tab. The code is closed.
• Errbit: An older Airbrake-compatible error catcher.
• Forgejo: A community forge, GPL-3.0 since v9.
• Gatus: A health dashboard with a status page in the config file.
• Gitea: A lightweight Git forge.
• GitHub Copilot: GitHub's coding assistant. Free is capped. The code is not public.
• GitLab Community Edition: The MIT edition of GitLab, without EE.
• GlitchTip: Error tracking compatible with Sentry SDKs.
• Highlight: Session replay and errors, with a split license.
• Kener: A status page with incidents, maintenance, and email subscriptions.
• llama.cpp: LLM inference in C and C++. The license is MIT. llama-server speaks an OpenAI-style API.
• Ollama: Run open models on your own computer. The license is MIT.
• OneUptime: Status pages plus monitors, incidents, and on-call.
• OpenCode: A terminal and desktop coding agent that can open a GitHub pull request.
• OpenHands: Agent Canvas, a self-hosted control center for coding agents.
• Radicle: A peer-to-peer code forge.
• SigNoz: Traces, metrics, and logs in one app.
• SourceHut: Git hosting composed of small services.
• Tabby: A self-hosted completion server. Community is free for up to 5 users.
• Uptime Kuma: Uptime checks, with a public status page of those checks.

Where we looked

• https://docs.vllm.ai
• https://github.com/vllm-project/vllm
• https://raw.githubusercontent.com/vllm-project/vllm/main/README.md
• https://raw.githubusercontent.com/vllm-project/vllm/main/LICENSE