AWS doubles down on custom LLMs with features meant to simplify model creation

Right on the heels of announcing Nova Forge, a service to train custom Nova AI models, Amazon Web Services (AWS) announced more tools for enterprise customers to create their own frontier models. AWS announced new capabilities in Amazon Bedrock and Amazon SageMaker AI at its AWS re:Invent conference on Wednesday. These new capabilities are designed to make building and fine-tuning custom large language models (LLMs) easier for developers. The cloud provider is introducing serverless model customization in SageMaker, which allows developers to start building a model without needing to think about compute resources or infrastructure, according to Ankur Mehrotra, general manager of AI platforms at AWS, in an interview with TechCrunch. To access these serverless model-building capabilities, developers can either follow a self-guided point-and-click path or an agent-led experience where they can prompt SageMaker using natural language. The agent-led feature is launching in preview. “If you’re a healthcare customer and you wanted a model to be able to understand certain medical terminology better, you can simply point SageMaker AI, if you have labeled data, then select the technique and then off SageMaker goes, and [it] fine tunes the model,” Mehrotra said. This capability is available for customizing Amazon’s own Nova models and certain open source models (those with publicly available model weights), including DeepSeek and Meta’s Llama. AWS is also launching Reinforcement Fine-Tuning in Bedrock that allows developers to choose either a reward function or a pre-set workflow, and Bedrock will run a model customization process automatically from start to finish. Techcrunch event San Francisco | October 13-15, 2026 Frontier LLMs — meaning the most advanced AI models — and model customization appear to be an area of focus for AWS at this year’s conference. AWS announced Nova Forge, a service where AWS will build custom Nova models for its enterprise customers for $100,000 a year, during AWS CEO Matt Garman’s keynote on Tuesday. “A lot of our customers are asking, ‘If my competitor has access to the same model, how do I differentiate myself?’” Mehrotra said. “‘How do I build unique solutions that are optimized, that optimize my brand, for my data, for my use case, and how do I differentiate myself?’ What we’ve found is that, the key to solving that problem is being able to create customized models.” AWS has yet to gain a substantial user base for its AI models. A July survey from Menlo Ventures found that enterprises greatly prefer Anthropic, OpenAI, and Gemini to other models. However, the ability to customize and fine-tune these LLMs could start to give AWS a competitive advantage. Follow along with all of TechCrunch’s coverage of the annual enterprise tech event here, and see all the announcements you may have missed thus far here.