Reflection AI debuts Beam, a 501B open model

Reflection AI has released Beam, its first open-weight language model, according to the company's announcement. The model carries 501 billion parameters and is positioned for both general text generation and reasoning workloads.

Notably, Beam is a dense model rather than a mixture-of-experts design — a choice that sets it apart from many recent frontier-scale releases, which have leaned on sparse architectures to keep inference costs down. A dense model at this size signals a bet on raw capability, though it also implies substantial hardware requirements to run.

Why it matters

Open-weight models in the half-trillion-parameter range remain rare, and each new entrant expands the options available to researchers and builders who want to inspect, fine-tune, or self-host large systems rather than rely on closed APIs.

• Scale: 501B parameters, dense architecture
• Focus: text generation and reasoning
• Access: open weights under a custom license

Key details — including context length and benchmark results — were not specified in the release record, and the model ships under a custom license rather than a standard open-source one, so teams will want to review the terms before building on it. Reflection's blog post is the authoritative source for the full picture.