Beam 1.0 501B A23B
reflection/beam-1.0-501b-a23bInputOutput
Compare its 4 providersIncident RSSCompare with GLM 5.3, DeepSeek V4.1 Flash, GLM 5.2
CompareBeam 1.0 501B A23B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 86.58% | 100% | 100% | 491ms | 2.78s | 158 tps | 1.0M | $1.00 / $3.00 | |
Togethertogether | Healthy | 100% | 89.23% | 88.57% | 88.57% | 10.6s | 18.9s | 15 tps | 1.0M | $0.400 / $1.20 |
| Down | 20.00% | 83.63% | 7.14% | 7.14% | 16.9s | 59.2s | 6.0 tps | 1.0M | $0.250 / $1.00 | |
| No data | — | 100% | 100% | 100% | 134ms | 806ms | 516 tps | 1.0M | $1.30 / $4.30 |
- CoreWeave100%Healthy24h 86.58%
- 7d
- 100%
- 30d
- 100%
- p50
- 491ms
- p99
- 2.78s
- Throughput
- 158 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.00
coreweave/fp4fp4 - Together100%Healthy24h 89.23%
- 7d
- 88.57%
- 30d
- 88.57%
- p50
- 10.6s
- p99
- 18.9s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $0.400 / $1.20
together - Nebius20.00%Down24h 83.63%
- 7d
- 7.14%
- 30d
- 7.14%
- p50
- 16.9s
- p99
- 59.2s
- Throughput
- 6.0 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.00
nebius/fp8fp8 - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 134ms
- p99
- 806ms
- Throughput
- 516 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $4.30
baseten/fp4fp4
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
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.
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%.