Reflection AI has introduced Beam, its first model, with 501 billion total parameters and 23 billion active parameters. The company describes it as an agentic open model trained end to end from scratch.
The announcement comes before the full weights release. Reflection's launch post says the weights are due later in October 2026, meaning the complete weights were not yet public when the company introduced Beam.
Four weeks of pretraining
Reflection says it pretrained Beam in four weeks on 24 trillion tokens. The company credits work on mixture-of-experts stability, large-scale data curation and deduplication for building the model's foundation.
Ioannis Antonoglou, a member of the Reflection team, said pretraining began in July. He described Beam as a first milestone toward the company's goal of making open intelligence broadly accessible, and said Reflection is already training a larger successor.
What Reflection plans to release
Antonoglou said the company plans to publish Beam's full weights, model card and technical report later in October. Team member Alex Polozov added that the weights are planned under the Apache 2.0 license, alongside a detailed technical report and integrations with open-source partners.
Until those materials are public, the model specifications and performance descriptions remain claims from Reflection and its team.
