AI Model Hosting and Inference

The National Institute of Standards and Technology (NIST) is seeking information from contractors capable of providing open-weight AI model hosting and inference services. The required services include quick-turn hosting, accurate inference, automatic and rapid inference scaling, hosting access to many models, data retention, reliability, and cost-effective hosting and inference for models. The purpose of this Sources Sought Notice is to identify responsible sources capable of performing the required services, determine the availability of small businesses, and assess industry experience with AI model hosting and inference services. * The contractor must be able to support newly-released models within the first few business days after they become available. * The contractor must be able to provide accurate inference, including reasoning and tool calling performance. * The contractor must be able to support rapid scaling of inference usage without requiring that NIST reserve all needed inference capacity in advance. * The contractor must be able to host a large selection of models by default and be able to quickly host open-weight models on-demand for NIST. * The contractor must not retain inference data. * The contractor must have high uptime for its inference services. * The contractor must be able to provide hosting and inference for models at a price that is in line with typical industry pricing.