Beam 1.0 501B A23B: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 241ms◆ (best) | 688ms◆ (best) | 592 tps◆ (best) | 1.0M | $1.30 / $4.30 | |
| Healthy | 100%◆ (best) | 88.96% | 100%◆ (best) | 100%◆ (best) | 766ms | 8.09s | 105 tps | 1.0M | $1.00 / $3.00 | |
Togethertogether | Degraded | 100%◆ (best) | 90.19% | 96.77% | 96.77% | 17.2s | 76.8s | 6.0 tps | 1.0M | $0.400 / $1.20 |
| Down | 60.00% | 82.59% | 48.71% | 48.71% | 30.4s | 83.5s | 4.0 tps | 1.0M | $0.250 / $1.00◆ (best) |
- BaseTen100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 241ms◆ (best)
- p99
- 688ms◆ (best)
- Throughput
- 592 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $1.30 / $4.30
baseten/fp4fp4 - CoreWeave100%◆ (best)Healthy24h 88.96%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 766ms
- p99
- 8.09s
- Throughput
- 105 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.00
coreweave/fp4fp4 - Together100%◆ (best)Degraded24h 90.19%
- 7d
- 96.77%
- 30d
- 96.77%
- p50
- 17.2s
- p99
- 76.8s
- Throughput
- 6.0 tps
- Context
- 1.0M
- $/Mtok
- $0.400 / $1.20
together - Nebius60.00%Down24h 82.59%
- 7d
- 48.71%
- 30d
- 48.71%
- p50
- 30.4s
- p99
- 83.5s
- Throughput
- 4.0 tps
- Context
- 1.0M
- $/Mtok
- $0.250 / $1.00◆ (best)
nebius/fp8fp8
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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, averaged over the hour.
Throughput
Median tokens per second.