AI Agent StoreReflection · Weights and hosted access available
Reflection Beam
A text model for coding and multi-step work with tools. You can now download it under Apache 2.0 or use a hosted service. Choose hosting for a simpler start; running the full model yourself requires substantial hardware.
Released 2026-10-05 · First reviewed 2026-10-07 · Checked 2026-11-03. Announced October 5; weights and broader hosted access became available October 16.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact provider API ID: Beam-1.0-501B-A23B. Beam supports tools and structured answers, with low, medium, high, xhigh and max thinking. None and minimal are unsupported. Reflection documents defaults that can differ by organization; check your account’s model response. The documented API name is now Beam-1.0-501B-A23B; this documentation change alone does not establish a new checkpoint or improved quality.
Available thinking settings: low, medium, high, xhigh, max. We do not yet have comparable independent results for these settings. The default applied when a request omits effort is unverified.
Reflection released weights on October 16 under Apache 2.0. Gateway’s reflection/beam is temporarily free when served by Reflection and automatically becomes paid when that offer ends. reflection/beam-free instead stops serving at the end. Check the selected provider and current terms.
Reflection documents 1,048,576 combined input/output tokens and up to 131,072 output tokens. Your plan may allow less. Requests that ask for token probabilities (logprobs) allow at most 8,192 output tokens, including thinking. Set an output budget that fits alongside your prompt.
Current OpenRouter rates are shown separately. Use the prices for the service your application calls. Inspect the separate OpenRouter offer ↗
Gateway’s Reflection-served offer is temporarily free; neither quote sets your direct Reflection account price. Check the chosen service before budgeting for ongoing use. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Check availability and plans ↗
More setup and licensing details ↗
More setup and licensing details ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗