Serverless Inference API endpoints for running pre-deployed AI models without managing infrastructure. Access a curated catalog of large language models, vision models, and embeddings hosted on Vultr. Built-in support for vector storage with RAG, tool calling, and streaming responses.
Evaluating Serverless Inference for production? Our team can scope capacity, pricing, and migration.
Contact SalesDeploying a large language model traditionally means provisioning GPU infrastructure and managing scaling logic yourself, even when traffic is unpredictable. In this video, we walk through provisioning a Vultr Serverless Inference subscription from the Vultr Console, covering available models, pricing, and the built-in Prompt and Chat tools for testing models directly in the browser. To try Vultr Serverless Inference yourself, get started with $250 in free credits on a new Vultr account: https://www.vultr.com/promo/try250/ To ask questions, share feedback, or connect with other developers using Vultr Serverless Inference, join the discussion in the Vultr Community Forum: https://community.vultr.com/ Docs and Resources: Vultr Serverless Inference Product Documentation: https://docs.vultr.com/products/compute/serverless-inference/provisioning Vultr API Documentation: https://www.vultr.com/api/#tag/serverless-inference/operation/create-inference Vultr Reference Documentation: https://docs.vultr.com/reference
Creators(x) Spotlight: Mirdul Swarup – Building in the Open
October 1, 2026
Stealthium Joins the Vultr Cloud Alliance to Bring GPU Observability and Runtime Security to AI Infrastructure
September 30, 2026
Wasabi Joins the Vultr Cloud Alliance to Deliver Greater Cloud Flexibility and Better Economics
September 29, 2026
