Reflection · Model identity
Beam 1.0 501B A23B
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
1pricing route
What published route metadata supports
CachingHugging FaceReasoningStructured outputTool use
Input modalities
Text
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Only source-backed fields are filled
Release dateNot independently verified
Knowledge cutoffNot independently verified
Open weightsNot independently verified
OpenRouter catalog date2026-10-16
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
Could this workload cost less?Compare Beam 1.0 501B A23B with cheaper models using the same workload.
Find cheaper alternatives →| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterStandard | reflection/beam-1.0-501b-a23b | $0.25 | $0.05 | $1 | 1.05M | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
2 verified price changes since Aug 26, 2026
1 route availability change recorded. No earlier prices are inferred.
Input / 1M$0.25Oct 17, 2026 → Oct 24, 2026
Output / 1M$1Oct 17, 2026 → Oct 20, 2026
- Oct 24, 2026OpenRouter · Standard
Input $0.3 → $0.25 · Cached input $0.04 → $0.05
- Oct 20, 2026OpenRouter · Standard
Input $1 → $0.3 · Cached input $0.1 → $0.04 · Output $3 → $1
- Oct 17, 2026OpenRouter · Standard
New pricing route added