Beam 1.0 501B A23B

by Reflection · reflection/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...

Input / 1M tokens
$0.25
Output / 1M tokens
$1.00
Context
1.05M

Specs

Input price$0.25 / 1M tokens
Output price$1.00 / 1M tokens
Cached input$0.05 / 1M tokens
Context window1.05M tokens
Max output131K tokens
Readstext
Writestext
Tool callingYes
ReasoningYes
ListedOct 16, 2026

List prices in USD, updated Oct 30, 2026. Providers may charge differently.

Providers

5 providers serve this model, as of Oct 30, 2026, 18:12 UTC.

Providers serving this model, sorted by price
ProviderQuantizationContextMax outputInput / 1MOutput / 1MCache read / 1MUptime (30 min)Latency (median)Throughput (median)SupportsStatus
NebiusCheapestfp41.05M131K$0.25$1.00$0.05100%778 ms134 tok/sNormal
CoreWeavefp41.05M944K$0.30$1.00$0.04100%415 ms198 tok/sNormal
BaseTenFastestfp41.05M131K$0.40$1.20$0.04—374 ms436 tok/sNormal
DigitalOcean—1.05M944K$0.40$1.20$0.04100%456 ms156 tok/sNormal
Together—1.05M131K$0.40$1.20$0.04100%172 ms175 tok/sNormal

"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.