Runpod Blog.

We sponsored TreeHacks 2026 at Stanford, where teams built on Runpod across 36 hours, shipping projects ranging from GPU-accelerated cancer drug discovery to real-time brain-to-music generation. Our top prizes went to RepoRx, NeuroBlocks, HackOverflow, and ADapt.

If you've been using Claude Code with Anthropic's hosted models, you already know how powerful it is for AI-assisted development. But what if you could run the same workflow for a fraction of the cost, with complete control over the underlying model? In this guide, we'll walk you through connecting Claude Code to a self-hosted model running on Runpod using Ollama — no Anthropic API key required.

A quick run through of how to set up Claude Code in a pod on Runpod

Join us as we celebrate our fielding of our 10 billionth serverless request.

Runpod surpasses $120M ARR, now serving over 500,000 developers worldwide. Founder Zhen reflects on the journey from basement GPU rigs to AI-first cloud infrastructure powering startups, research labs, and Fortune 500 teams.

Deploy Serverless endpoints directly from GitHub and roll back instantly if needed. Runpod’s improved GitHub integration lets you revert to previous builds without rebuilding Docker images, enabling faster, safer, and more confident deployments.

In early December 2025, Mistral AI released Mistral Large 3 and Devstral 2, two open models under the Apache 2.0 license, with Mistral Large 3 targeting frontier-scale reasoning and long-context workloads and Devstral 2 focusing on developer use cases like coding and agent workflows. At the same time, Nvidia expanded its open source footprint with the release of the Nemotron 3 model family and the acquisition of SchedMD, reinforcing a broader shift toward open models and open infrastructure that teams can run, benchmark, and scale on their own GPU platforms.