GLM 5.1
z-ai/glm-5.1
Compare with GLM 5, GLM 5 Turbo, GLM 5V Turbo
CompareGLM 5.1
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.79% | 99.76% | 99.76% | 1.57s | 11.8s | 48 tps | 203K | $1.26 / $3.96 | |
| Healthy | 100% | 99.70% | 99.39% | 99.39% | 633ms | 3.98s | 48 tps | 203K | $1.20 / $4.40 | |
| Healthy | 100% | 99.41% | 99.34% | 99.34% | 1.09s | 8.29s | 55 tps | 203K | $1.05 / $3.50 | |
Friendlifriendli | Healthy | 100% | 99.97% | 99.95% | 99.95% | 259ms | 6.67s | 80 tps | 203K | $1.40 / $4.40 |
| Healthy | 100% | 99.63% | 99.62% | 99.62% | 1.51s | 6.49s | 50 tps | 203K | $0.910 / $2.86 | |
| Healthy | 100% | 97.79% | 97.33% | 97.33% | 672ms | 4.42s | 30 tps | 203K | $1.40 / $4.40 | |
| Healthy | 100% | 99.24% | 99.61% | 99.61% | 662ms | 12.3s | 84 tps | 203K | $1.40 / $4.40 | |
| Healthy | 100% | 99.91% | 99.88% | 99.88% | 1.64s | 5.62s | 44 tps | 205K | $1.19 / $3.74 | |
| Healthy | 100% | 99.27% | 98.73% | 98.73% | 2.69s | 10.9s | 24 tps | 200K | $0.966 / $3.04 | |
| Healthy | 100% | 97.11% | 96.07% | 96.07% | 1.12s | 8.02s | 75 tps | 200K | $1.54 / $4.84 | |
| Healthy | 100% | 99.54% | 99.00% | 99.00% | 4.57s | 7.42s | 19 tps | 203K | $1.40 / $4.40 | |
| No data | — | 99.84% | 99.75% | 99.75% | 1.82s | 2.97s | 58 tps | 203K | $1.33 / $4.18 | |
| No data | — | 99.96% | 99.89% | 99.89% | 956ms | 7.00s | 69 tps | 203K | $1.40 / $4.40 | |
| No data | — | 81.13% | 83.73% | 83.73% | 2.29s | 81.3s | 26 tps | 203K | $0.980 / $3.08 | |
DigitalOceandigitalocean | No data | — | 96.15% | 93.76% | 93.76% | 1.33s | 12.6s | 19 tps | 164K | $1.30 / $4.30 |
| No data | — | 99.82% | 99.31% | 99.31% | 4.28s | 11.5s | 32 tps | 205K | $1.38 / $4.40 | |
Phalaphala | No data | — | 80.99% | 83.76% | 83.76% | 2.52s | 18.3s | 25 tps | 203K | $1.21 / $4.20 |
- AtlasCloud100%Healthy24h 99.79%
- 7d
- 99.76%
- 30d
- 99.76%
- p50
- 1.57s
- p99
- 11.8s
- Throughput
- 48 tps
- Context
- 203K
- $/Mtok
- $1.26 / $3.96
atlas-cloud/fp8fp8 - Crusoe100%Healthy24h 99.70%
- 7d
- 99.39%
- 30d
- 99.39%
- p50
- 633ms
- p99
- 3.98s
- Throughput
- 48 tps
- Context
- 203K
- $/Mtok
- $1.20 / $4.40
crusoe/fp8fp8 - DeepInfra100%Healthy24h 99.41%
- 7d
- 99.34%
- 30d
- 99.34%
- p50
- 1.09s
- p99
- 8.29s
- Throughput
- 55 tps
- Context
- 203K
- $/Mtok
- $1.05 / $3.50
deepinfra/fp4fp4 - Friendli100%Healthy24h 99.97%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 259ms
- p99
- 6.67s
- Throughput
- 80 tps
- Context
- 203K
- $/Mtok
- $1.40 / $4.40
friendli - GMICloud100%Healthy24h 99.63%
- 7d
- 99.62%
- 30d
- 99.62%
- p50
- 1.51s
- p99
- 6.49s
- Throughput
- 50 tps
- Context
- 203K
- $/Mtok
- $0.910 / $2.86
gmicloud/fp8fp8 - Nebius100%Healthy24h 97.79%
- 7d
- 97.33%
- 30d
- 97.33%
- p50
- 672ms
- p99
- 4.42s
- Throughput
- 30 tps
- Context
- 203K
- $/Mtok
- $1.40 / $4.40
nebius/fp8fp8 - Parasail100%Healthy24h 99.24%
- 7d
- 99.61%
- 30d
- 99.61%
- p50
- 662ms
- p99
- 12.3s
- Throughput
- 84 tps
- Context
- 203K
- $/Mtok
- $1.40 / $4.40
parasail/fp8fp8 - SiliconFlow100%Healthy24h 99.91%
- 7d
- 99.88%
- 30d
- 99.88%
- p50
- 1.64s
- p99
- 5.62s
- Throughput
- 44 tps
- Context
- 205K
- $/Mtok
- $1.19 / $3.74
siliconflow/fp8fp8 - StreamLake100%Healthy24h 99.27%
- 7d
- 98.73%
- 30d
- 98.73%
- p50
- 2.69s
- p99
- 10.9s
- Throughput
- 24 tps
- Context
- 200K
- $/Mtok
- $0.966 / $3.04
streamlake/fp8fp8 - Venice100%Healthy24h 97.11%
- 7d
- 96.07%
- 30d
- 96.07%
- p50
- 1.12s
- p99
- 8.02s
- Throughput
- 75 tps
- Context
- 200K
- $/Mtok
- $1.54 / $4.84
venice/fp8fp8 - Z.AI100%Healthy24h 99.54%
- 7d
- 99.00%
- 30d
- 99.00%
- p50
- 4.57s
- p99
- 7.42s
- Throughput
- 19 tps
- Context
- 203K
- $/Mtok
- $1.40 / $4.40
z-ai/fp8fp8 - No data24h 99.84%
- 7d
- 99.75%
- 30d
- 99.75%
- p50
- 1.82s
- p99
- 2.97s
- Throughput
- 58 tps
- Context
- 203K
- $/Mtok
- $1.33 / $4.18
alibaba/fp8fp8 - No data24h 99.96%
- 7d
- 99.89%
- 30d
- 99.89%
- p50
- 956ms
- p99
- 7.00s
- Throughput
- 69 tps
- Context
- 203K
- $/Mtok
- $1.40 / $4.40
baidu/fp8fp8 - No data24h 81.13%
- 7d
- 83.73%
- 30d
- 83.73%
- p50
- 2.29s
- p99
- 81.3s
- Throughput
- 26 tps
- Context
- 203K
- $/Mtok
- $0.980 / $3.08
chutes/fp8fp8 - No data24h 96.15%
- 7d
- 93.76%
- 30d
- 93.76%
- p50
- 1.33s
- p99
- 12.6s
- Throughput
- 19 tps
- Context
- 164K
- $/Mtok
- $1.30 / $4.30
digitalocean - No data24h 99.82%
- 7d
- 99.31%
- 30d
- 99.31%
- p50
- 4.28s
- p99
- 11.5s
- Throughput
- 32 tps
- Context
- 205K
- $/Mtok
- $1.38 / $4.40
novita/fp8fp8 - No data24h 80.99%
- 7d
- 83.76%
- 30d
- 83.76%
- p50
- 2.52s
- p99
- 18.3s
- Throughput
- 25 tps
- Context
- 203K
- $/Mtok
- $1.21 / $4.20
phala
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- GLM 5.1DigitalOceandigitalocean$0.975 / $4.30 → $1.30 / $4.302026-08-21 03:31 UTC
- GLM 5.1Baidubaidu/fp8$0.896 / $2.82 → $1.40 / $4.402026-08-20 23:41 UTC
- GLM 5.1Baidubaidu/fp8$1.04 / $3.26 → $0.896 / $2.822026-08-20 13:46 UTC
- GLM 5.1Baidubaidu/fp8$1.40 / $4.40 → $1.04 / $3.262026-08-20 12:46 UTC
- GLM 5.1Baidubaidu/fp8$0.896 / $2.82 → $1.40 / $4.402026-08-19 23:40 UTC
- GLM 5.1Baidubaidu/fp8$0.952 / $2.99 → $0.896 / $2.822026-08-19 13:45 UTC
- GLM 5.1Baidubaidu/fp8$1.40 / $4.40 → $0.952 / $2.992026-08-19 12:40 UTC
History
6 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.
Throughput
Median tokens per second.