Frequently Asked Questions (FAQs) About Vultr Serverless Inference

Vultr Serverless Inference supports a growing catalog of production-ready models across multiple categories, including large language models, chat-optimized models, code generation models, text-to-speech models, and image generation models. The available model list is regularly updated as new models are added. To view the current supported models, navigate to the Serverless Inference section in the Vultr Console and check the model selector in the Prompt tab.