Build your website with Cloud Run using your favorite language or framework (Go, Python, Java, Node.js, .NET, and more), access your SQL database on Cloud SQL, and render dynamic HTML pages.

Use Cloud Run GPUs to power real-time inference with open-source models such as Gemma 3, Llama 3.2, or custom fine-tuned models. Build chatbots, generate on-the-fly document summaries, and more—all while scaling to handle unpredictable traffic spikes. Or, with GPUs on Cloud Run functions your data scientist can run Python scripts and perform event-driven inference with limited knowledge of the underlying infrastructure.

Cloud Run jobs are ideal for running parallel data processing tasks that need to complete quickly due to latency concerns.

Use Cloud Run functions to surface your own microservices using HTTP APIs or integrate with third-party services that offer webhook integrations to quickly extend your application with powerful capabilities, such as sending a confirmation email after a successful Stripe payment or responding to Twilio text message events.

Request-response flow between the gen AI app and its users. Runs LangChain to orchestrate retrieval-augmented generation (RAG), prepare prompts, call inference endpoint, streams response.