Open-weight large language model
Beam 1.0
Beam 1.0 is Reflection AI's first open-weight model, a sparse mixture-of-experts language model with 501B total and 23B active parameters and a 1M-token context. Announced on 5 October 2026 and released under Apache 2.0 on 16 October 2026, it is a text-only model built for coding, reasoning and agentic workloads.
Last reviewed 28 Oct 2026 · by Reflection AI
Facts at a glance
| Developer | Reflection AI |
|---|---|
| Released | Announced 5 October 2026; weights released 16 October 2026 source |
| Parameters | 501.3B total, 23.4B active (256 experts, 52 layers) source |
| Context window | 1M tokens source |
| Knowledge cutoff | 30 June 2026 source |
| License | Apache 2.0 |
| Formats | BF16, FP8 and NVFP4 weights plus a speculative decoding drafter source |
| Pretraining data | 23.8T tokens source |
What Beam is used for
Reflection positions Beam for coding, reasoning and agentic work. The model card lists text input and output only and says the model was developed predominantly for English. Reflection says the weights have day-zero support in Transformers, vLLM, SGLang, Unsloth, Axolotl, TokenSpeed and NVIDIA Dynamo, and that the model is offered on clouds and hosts including AWS, Google Cloud, Microsoft Foundry, Oracle, Together AI and OpenRouter.
Questions people ask
- What license does Beam use?
- Apache 2.0, according to Reflection's model card and its 16 October 2026 release post.
- How many parameters does Beam have?
- 501.3B in total with 23.4B active per token, in a 256-expert mixture-of-experts design, per the model card.