Reflection AI Unveils Beam, a 501B-Parameter Open-Weight Model
Beam is a text-only mixture-of-experts model with 23 billion active parameters; Reflection says weights will be released this month.
Reflection AI unveiled Beam, its first frontier open-weight AI model, on October 5, 2026. The model is a text-only mixture-of-experts system with 501 billion total parameters and 23 billion active parameters. It was pre-trained on 23.8 trillion tokens and offers a 1 million token context window, according to techcrunch.com.
Reflection says Beam matches the performance of leading Chinese open models on advanced reasoning benchmarks at dramatically lower costs. The company also says Beam outperforms leading Western open models and uses 3-4x less inference compute. Reflection says it will release Beam's weights and full technical details this month.
Built on a large funding base
Reflection AI was founded in 2024 by two former Google DeepMind researchers. The company has raised roughly $4.7 billion from backers including Nvidia, Sequoia Capital, and Lightspeed Venture Partners. Its last round valued Reflection at a $25 billion pre-money valuation.
In the summer of 2026, Reflection signed deals collectively worth more than $7 billion with SpaceX and Nebius to secure access to Nvidia's GB300 chips through 2029. Axios reported that Reflection was close to launching Beam before the announcement.
Quick answers
What is Beam, Reflection AI's new model?
Beam is Reflection AI's first frontier open-weight AI model. It is a text-only mixture-of-experts model with 501 billion total parameters and 23 billion active parameters.
When will Beam's weights be released?
Reflection says it will release Beam's weights and full technical details this month, in October 2026.
What context window does Beam have?
Beam has a 1 million token context window and was pre-trained on 23.8 trillion tokens.