Replicate

A router for LLMs and other AI models

Run and fine-tune generative AI models with simple APIs and scalable GPU clusters. Train & deploy at scale on The AI Acceleration Cloud.

Detect your hardware and find out which AI models you can run locally. GPU, CPU, and RAM analysis in your browser.

Run AI on your own terms — connect any model, extend with code, and protect what matters, fully self-hosted.

Bring your own code, and run CPU, GPU, and data-intensive compute at scale. The serverless platform for AI and data teams.

Run local AI models like gpt-oss, Llama, Gemma, Qwen, and DeepSeek privately on your computer.

Spawn coding agents that run infinitely in the cloud. Powered by AI SDK, Gateway, Sandbox, and Workflow SDK.

The open source AI coding agent for the terminal — bring your own model, works with Claude, OpenAI, Google, and local models.

The most advanced AI code reviews that catches 95%+ bugs. Free your devs to ship code faster.

Deploy app servers close to your users — a cloud for developers who want fast, global, low-fuss compute.