Reflection releases Beam, an Apache 2.0 open-weight coding model
Reflection released the weights of Beam, a 501B-parameter (23B active) mixture-of-experts model for coding, reasoning and agent work, on Hugging Face under the Apache 2.0 license, with an open-source terminal harness called Mirror CLI.
What happened
- On October 16, 2026, Reflection published Beam's weights on Hugging Face under Apache 2.0, in BF16, FP8 and NVFP4 formats, plus a speculative-decoding drafter model.
- Beam is a sparse mixture-of-experts model with 501B total and 23B active parameters. Reflection says it was built for advanced coding, reasoning and long-horizon agentic workloads.
- Reflection also released Mirror CLI, an open-source terminal harness for running Beam as a coding agent, and lists support in vLLM, SGLang, Transformers, Unsloth and other tools.
- Beam is available through Reflection's API (public beta) and partner platforms, which Reflection says include OpenRouter, Ollama, LM Studio and Cloudflare.
Why it matters: Apache 2.0 means you can fine-tune Beam and ship it in commercial products without a custom license. Self-hosting a model this size needs data-center GPUs, so most people will try it through a hosted provider first.
Sources
- Reflection: Beam is now available reflection.ai
- Hugging Face model card huggingface.co
Checked October 17, 2026 against the sources above. Claims about performance or benchmarks are the company's own unless stated otherwise.