modelstatus.dev

Beam 1.0 501B A23B

reflection/beam-1.0-501b-a23bInputtextOutputtext

Compare its 4 providersIncident RSSCompare with GLM 5.3, DeepSeek V4.1 Flash, GLM 5.2

CompareBeam 1.0 501B A23B
  • Healthy24h 88.09%
    7d
    100%
    30d
    100%
    p50
    655ms
    p99
    5.65s
    Throughput
    119 tps
    Context
    1.0M
    $/Mtok
    $1.00 / $3.00
    coreweave/fp4fp4
  • Healthy24h 89.99%
    7d
    94.74%
    30d
    94.74%
    p50
    11.9s
    p99
    34.4s
    Throughput
    10 tps
    Context
    1.0M
    $/Mtok
    $0.400 / $1.20
    together
  • Nebius0.00%
    Down24h 83.17%
    7d
    40.53%
    30d
    40.53%
    p50
    40.1s
    p99
    94.0s
    Throughput
    3.0 tps
    Context
    1.0M
    $/Mtok
    $0.250 / $1.00
    nebius/fp8fp8
  • No data24h 100%
    7d
    100%
    30d
    100%
    p50
    299ms
    p99
    1.02s
    Throughput
    346 tps
    Context
    1.0M
    $/Mtok
    $1.30 / $4.30
    baseten/fp4fp4

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 4 endpoints · 1 day with data, 2 endpoint-days below 90%.