Claude Code is now FREE: Here’s how…
The video outlines three free methods to run Claude Code without paying for Anthropic's API: using Ollama with the cloud-based GLM 5.1 model, using Ollama with Google's locally-run Gemma 4 model, and connecting to a free testing model called Elephant Alpha via OpenRouter. Each method is presented as taking under 5 minutes to set up and requires no coding experience.
Summary
The video opens by claiming that Claude Code — normally a paid AI coding tool tied to Anthropic's API — can be used entirely for free through three distinct methods. The host explains that Claude Code functions as an interface that can be decoupled from Anthropic's models and pointed at alternative AI models, including free or locally-run ones, without any loss of core functionality.
The first method involves using a tool called Ollama paired with GLM 5.1, a cloud-based model. The host walks through downloading Ollama, navigating to the model section of the Ollama website, copying the GLM 5.1 run command, and pasting it into the terminal. This approach is described as fast and capable but subject to token limits, making it best suited for smaller or medium-sized projects.
The second method, presented as the recommended option for most users, also uses Ollama but pairs it with Gemma 4, a model made by Google that runs entirely locally on the user's machine. Once downloaded via the command 'ollama run gemma4,' the model requires no internet connection, has no token limits, and incurs no ongoing costs. The host demonstrates this with a practical example: asking Claude Code to generate a full HTML landing page, which it completes without the user writing any code.
The third method uses a platform called OpenRouter, described as a marketplace for AI models. The host highlights a model called Elephant Alpha, which is currently free because it is in a public testing phase. Users create a free OpenRouter account, obtain an API key, and use a configuration tool called Spawn to connect the key to Claude Code. The host acknowledges that free testing models rotate on OpenRouter but notes that a free option has consistently been available every month for the past year.
The video also includes several practical use case examples — building email sequences, member dashboards, and onboarding guides — all generated via Claude Code with zero cost. The host concludes with a summary comparison of all three options and promotes two paid and free communities: the AI Profit Boardroom and the AI Success Lab.
Key Insights
- The host explains that Claude Code functions as an interface independent of Anthropic's models, meaning it can be redirected to any compatible model — including free or local ones — without losing its core functionality.
- The host argues that running Gemma 4 locally via Ollama is the best option for most users because it has no token limits, no cloud dependency, and zero ongoing cost once downloaded.
- The host claims that Elephant Alpha on OpenRouter is free specifically because it is in a real-world testing phase, where AI companies release models publicly to gather feedback before full deployment.
- The host states that free testing models on OpenRouter rotate regularly and that a free model option has been available every single month for the past year, suggesting this is a reliable ongoing strategy.
- The host demonstrates that Claude Code can generate a complete HTML landing page from a single plain-language prompt, arguing this eliminates the need for a developer and produces real results at zero cost when using a local model.
Topics
Transcript
[0:00] Claude Code is free right now, not a trial, not a limited version, actually free. And most people have no idea this is even possible. I'm going to show you three ways to run Claude Code without paying a single penny. One of them runs entirely on your computer, no internet needed, no limits. One uses cloud models that are way more powerful than what most people pay for. And one uses a free API that barely anyone knows about right now. All three work today. All three take less than 5 minutes to set up. You don't need to be a developer. You don't need a big computer. You just need to [0:30] follow these steps. So, if…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
NEW Nvidia Autonomous AI is WILD!! 🤯
Nvidia announced Nemo Clo, a new autonomous AI agent system that operates independently without continuous prompting. Powered by Nemotron 3 Ultra (a 550 billion parameter model), the system is five times faster and cheaper than previous versions, with OpenShell providing secure sandboxed execution.
Laguna XS 2.1: New FREE + Opensource Local AI!
Julian reviews Laguna XS 2.1, a new free open-source local AI coding model from Poolside that performs comparably to Qwen 3.6 and outperforms Claude Haiku on benchmarks. He demonstrates its practical capabilities by building landing pages and functional apps, highlighting its speed, offline functionality, and multiple deployment options through local setup, Claude Code, or OpenRouter's free API.
How to Run Hermes FREE Forever!
The video demonstrates how to run the Hermes AI agent for free using Gemma 4, a local open-source model from Google, with significant speed improvements through MLX optimization. The setup works on Apple Silicon Macs or via free APIs on Open Router, enabling autonomous agents to work offline and privately without subscription costs.
This NEW Chinese AI is INSANE! (FREE + Open Source!)
Long Cap 2.0 is a new open-source Chinese AI model from a food delivery app company that offers 1 million tokens of free context memory, beats GPT-4.5 on SWE bench pro benchmarks, and uses efficient parameter activation to reduce computational overhead while maintaining high performance.
Claude Code is now FREE: Here’s how…
Google's new Gemma 4 model running on Ollama is 90% faster on Apple Silicon, enabling free Claude Code usage locally without token costs. The setup requires three simple steps: downloading Ollama, Gemma 4, and installing into Claude Code, with alternatives available via OpenRouter API for non-Mac users.