Beam 1.0 Beam 1.0 is Reflection AI's first open-weight large language model, a 501-billion parameter mixture-of-experts architecture with 23 billion active parameters and a 1 million token context window. Released under the Apache 2.0 license with BF16, FP8, and NVFP4 weights, tokenizer, reference implementation, DFlash2 drafter, and the open-source Mirror CLI harness. Designed for coding and long-horizon agentic tasks, it launched with an ecosystem of 40+ partners for inference, fine-tuning, and agents.
Visit productFeatured media
Loading media…
View on XCosigns Received
“We are excited to partner with Reflection to post-train their open-weight models for our customers! Beam is supported in AC2 and we're already seeing promising results from early training runs”
“🎉 Reflection-Beam-1.0 from @reflection_ai has Day-0 support in vLLM. 501B total parameters, 23B active per token, and a 1M-token context window. Beam combines hybrid attention with Harmony-format reasoning and tool use. Beam also has Day-0 RL support in SkyRL (@NovaSkyAI): LoRA, BF16 full fine-tuning and MXFP8 RL, with vLLM rollouts. We worked with @reflection_ai and @Inferact on the serving path, from fused kernels to DFlash. Here is what is under the hood. 🧵”
“Beam is a token-efficient, frontier-scale model for your coding agents, comes with its own harness 🔥 A23B/501B model, also comes with NVFP4 & FP8 and day-0 transformers support 🤗 check out our blog ⤵️”
“Welcome Beam! Congrats to @ReflectionAI on launching their first open-weight model. The 501B MoE model was trained on NVIDIA GB300 NVL72 and delivers over 70K tokens/sec/GPU on Blackwell Ultra out of the box on day 0. 🤗 Beam 1.0 NVFP4 checkpoint on @huggingface:”
“Beam is yours to build on. Open weights, Apache 2.0. Alongside Mirror CLI, the harness Reflection built and trained it on. Proud of this team. Let’s build! 🇺🇸”
“Beam is ready! 501B total and 23B active parameters. AA Intelligence Index score 30, #2 US open weights model. Apache 2.0 license.”
“Reflection AI’s Beam 1.0 is out today, a 501B MoE with 23B active under Apache 2.0. We ran a brief RL post-training run on it in AC2 that tripled its score on a challenging long-horizon agentic coding task in 40 steps, 0.07 to 0.215. We’re offering day 0 support in AC2 for inference and post-training.”