Models / reflection
Beam 1.0 501B A23B
by reflection ·
reflection/beam-1.0-501b-a23bBeam 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...
reasoningtool-usereleased 2026-10-16
Legal score · raw
-
not yet benchmarked
Context
1.05M
max output 131K
Input
$0.31
per 1M tokens
Output
$1.25
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.06
5.0x cheaper than uncached
Uncached input
$0.31
per 1M tokens
Capabilities
Modalities
in text
out text
Request parameters it accepts
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.