# Reflection releases Beam 1.0, a 501B open MoE

> The frontier AI startup's first open-weight model activates just 23B parameters per token while targeting reasoning, code, and tool use.

Published by The Open Weights on Oct 7, 2026. Canonical: https://theopenweights.com/news/beam-1-0-501b-a23b-llqb

## Key facts

- Company: Reflection
- Model: Beam 1.0 501B-A23B
- Version: 1.0
- Category: Reasoning
- Modalities: Code, Text / LLM, Reasoning
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 501B (mixture of experts)
- Active parameters: 23B
- Context window: 1.0M tokens
- Architecture: BeamForCausalLM
- Precision: BF16
- Weights size: 1002.7 GB
- Significance: major
- Published: 2026-10-07
- Last verified: 2026-10-17
- Hugging Face: https://huggingface.co/reflection/Beam-1.0-501B-A23B
- Canonical URL: https://theopenweights.com/news/beam-1-0-501b-a23b-llqb

Reflection has published Beam 1.0, a 501-billion-parameter mixture-of-experts model released under the permissive Apache 2.0 license. The weights are available on [Hugging Face](https://huggingface.co/reflection/Beam-1.0-501B-A23B), and the company lays out its reasoning behind the launch in an [announcement post](https://reflection.ai/blog/introducing-beam).

The headline design choice is sparsity. While the full model carries 501B parameters, only about 23B are active for any given token. That architecture lets Beam reach the capacity of a very large model while keeping per-token compute closer to a mid-sized dense system — a tradeoff that has become the default for ambitious open releases.

## What it's built for

Reflection positions Beam squarely as a reasoning model, with additional emphasis on code generation and tool use. Those are the workloads where extended, multi-step inference tends to pay off, and where sparse MoE designs have been competitive with far larger dense alternatives.

- 501B total parameters, roughly 23B active per token
- Apache 2.0 license, permitting commercial use
- Focus on reasoning, code, and tool-calling

Why it matters: Reflection is best known as a well-funded startup pursuing frontier capabilities, and an Apache-licensed MoE at this scale signals a serious commitment to the open-weights ecosystem rather than a token gesture. For teams building agentic or code-heavy systems, a permissively licensed model with large capacity and modest active compute is a meaningful option — though real-world evaluation against established open MoEs will determine where Beam lands.

## Get the model

- [Hugging Face](https://huggingface.co/reflection/Beam-1.0-501B-A23B)

## Sources

- [reflection/Beam-1.0-501B-A23B](https://huggingface.co/reflection/Beam-1.0-501B-A23B) — Hugging Face, Oct 7, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Reflection releases Beam 1.0, a 501B open MoE", The Open Weights, Oct 7, 2026, https://theopenweights.com/news/beam-1-0-501b-a23b-llqb