Reflection AI announces Beam, a 501B-parameter model whose weights it plans to release

On October 5, 2026 Reflection AI introduced Beam, which it calls its first open-weight model: a sparse mixture-of-experts model with 501 billion total and 23 billion active parameters, built for coding, reasoning, and agentic workloads. The announcement says Beam was pretrained on 23.8 trillion tokens and that midtraining extends its effective context length to 1M tokens. As of the announcement, Beam was undergoing final red-teaming and evaluations and was offered through an early-access sign-up; Reflection says it will release the weights under an Apache 2.0 license later in October, along with a technical report, model card, and developer artifacts. The announcement itself does not provide the weights, and USASI has not tested Beam.1

USASI. (2026, October 13). Reflection AI announces Beam, a 501B-parameter model whose weights it plans to release. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/reflection-ai-announces-beam-open-weight-model/

@misc{usasi_news_reflection_ai_announces_beam_open_weight_model,
  author = {{USASI}},
  title = {Reflection AI announces Beam, a 501B-parameter model whose weights it plans to release},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/reflection-ai-announces-beam-open-weight-model/}},
  note = {United States of America Superintelligence. Last updated 2026-10-13}
}