CompareGLM 5
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock | Healthy | 100% | 91.96% | 97.27% | 97.27% | 893ms | 5.09s | 103 tps | 203K | $1.00 / $3.20 |
| Healthy | 100% | 99.91% | 99.82% | 99.82% | 2.27s | 8.06s | 35 tps | 203K | $0.950 / $3.15 | |
| Healthy | 100% | 100% | 99.90% | 99.90% | 963ms | 3.04s | 33 tps | 203K | $0.700 / $2.24 | |
| Healthy | 100% | 99.73% | 99.51% | 99.51% | 798ms | 96.3s | 28 tps | 203K | $0.600 / $2.08 | |
| Healthy | 100% | 99.93% | 99.67% | 99.67% | 1.19s | 6.54s | 51 tps | 203K | $0.600 / $1.92 | |
| Healthy | 100% | 99.92% | 99.77% | 99.77% | 2.19s | 7.31s | 41 tps | 205K | $0.950 / $2.55 | |
| Healthy | 100% | 99.99% | 99.90% | 99.90% | 1.10s | 4.22s | 59 tps | 203K | $1.00 / $3.20 | |
| Healthy | 99.80% | 99.95% | 99.95% | 99.95% | 2.51s | 5.56s | 51 tps | 198K | $0.600 / $1.92 | |
DigitalOceandigitalocean | No data | — | 96.46% | 94.13% | 94.13% | 1.03s | 30.1s | 8.5 tps | 64K | $1.00 / $3.20 |
| No data | — | 100% | 99.99% | 99.99% | 1.82s | 8.73s | 61 tps | 203K | $1.00 / $3.20 | |
| No data | — | 96.71% | 95.01% | 95.01% | 1.11s | 3.38s | 26 tps | 198K | $1.00 / $3.20 |
- Amazon Bedrock100%Healthy24h 91.96%
- 7d
- 97.27%
- 30d
- 97.27%
- p50
- 893ms
- p99
- 5.09s
- Throughput
- 103 tps
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
amazon-bedrock - AtlasCloud100%Healthy24h 99.91%
- 7d
- 99.82%
- 30d
- 99.82%
- p50
- 2.27s
- p99
- 8.06s
- Throughput
- 35 tps
- Context
- 203K
- $/Mtok
- $0.950 / $3.15
atlas-cloud/fp8fp8 - Baidu100%Healthy24h 100%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 963ms
- p99
- 3.04s
- Throughput
- 33 tps
- Context
- 203K
- $/Mtok
- $0.700 / $2.24
baidu/fp8fp8 - DeepInfra100%Healthy24h 99.73%
- 7d
- 99.51%
- 30d
- 99.51%
- p50
- 798ms
- p99
- 96.3s
- Throughput
- 28 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.08
deepinfra/fp4fp4 - GMICloud100%Healthy24h 99.93%
- 7d
- 99.67%
- 30d
- 99.67%
- p50
- 1.19s
- p99
- 6.54s
- Throughput
- 51 tps
- Context
- 203K
- $/Mtok
- $0.600 / $1.92
gmicloud/fp8fp8 - SiliconFlow100%Healthy24h 99.92%
- 7d
- 99.77%
- 30d
- 99.77%
- p50
- 2.19s
- p99
- 7.31s
- Throughput
- 41 tps
- Context
- 205K
- $/Mtok
- $0.950 / $2.55
siliconflow/fp8fp8 - Z.AI100%Healthy24h 99.99%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 1.10s
- p99
- 4.22s
- Throughput
- 59 tps
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
z-ai/fp8fp8 - StreamLake99.80%Healthy24h 99.95%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 2.51s
- p99
- 5.56s
- Throughput
- 51 tps
- Context
- 198K
- $/Mtok
- $0.600 / $1.92
streamlake/fp8fp8 - No data24h 96.46%
- 7d
- 94.13%
- 30d
- 94.13%
- p50
- 1.03s
- p99
- 30.1s
- Throughput
- 8.5 tps
- Context
- 64K
- $/Mtok
- $1.00 / $3.20
digitalocean - No data24h 100%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 1.82s
- p99
- 8.73s
- Throughput
- 61 tps
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
novita/fp8fp8 - No data24h 96.71%
- 7d
- 95.01%
- 30d
- 95.01%
- p50
- 1.11s
- p99
- 3.38s
- Throughput
- 26 tps
- Context
- 198K
- $/Mtok
- $1.00 / $3.20
venice/fp8fp8
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 endpoints reporting no data are omitted from the charts.
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 · 11 endpoints · 4 days with data, 13 endpoint-days below 90%.
Price changes
- GLM 5DigitalOceandigitalocean$0.750 → $1.00 / $2.40 → $3.202026-08-21 03:26 UTC