GLM 4.7
z-ai/glm-4.7
Compare with GLM 4.7 Flash, GLM 4.6, GLM 4.6V
CompareGLM 4.7
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex | Healthy | 100% | 99.75% | 99.90% | 99.90% | 462ms | 8.40s | 115 tps | 200K | $0.600 / $2.20 |
| Healthy | 100% | 91.82% | 94.51% | 94.51% | 1.01s | 3.94s | 22 tps | 131K | $0.600 / $2.50 | |
| Healthy | 100% | 92.19% | 94.84% | 94.84% | 964ms | 5.62s | 23 tps | 198K | $0.550 / $2.65 | |
| Healthy | 99.75% | 95.61% | 96.48% | 96.48% | 898ms | 8.74s | 32 tps | 203K | $0.400 / $1.75 | |
| Degraded | 95.65% | 93.68% | 94.13% | 94.13% | 2.01s | 41.2s | 17 tps | 205K | $0.540 / $1.98 | |
| Degraded | 94.79% | 92.11% | 91.29% | 91.29% | 3.08s | 40.5s | 21 tps | 203K | $0.600 / $2.20 | |
| Degraded | 93.83% | 90.61% | 94.32% | 94.32% | 1.91s | 23.0s | 26 tps | 203K | $0.520 / $1.85 | |
| Degraded | 92.21% | 92.91% | 92.86% | 92.86% | 1.99s | 25.4s | 21 tps | 200K | $0.480 / $1.76 |
- Google100%Healthy24h 99.75%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 462ms
- p99
- 8.40s
- Throughput
- 115 tps
- Context
- 200K
- $/Mtok
- $0.600 / $2.20
google-vertex - Mancer 2100%Healthy24h 91.82%
- 7d
- 94.51%
- 30d
- 94.51%
- p50
- 1.01s
- p99
- 3.94s
- Throughput
- 22 tps
- Context
- 131K
- $/Mtok
- $0.600 / $2.50
mancer/fp4fp4 - Venice100%Healthy24h 92.19%
- 7d
- 94.84%
- 30d
- 94.84%
- p50
- 964ms
- p99
- 5.62s
- Throughput
- 23 tps
- Context
- 198K
- $/Mtok
- $0.550 / $2.65
venice/fp4fp4 - DeepInfra99.75%Healthy24h 95.61%
- 7d
- 96.48%
- 30d
- 96.48%
- p50
- 898ms
- p99
- 8.74s
- Throughput
- 32 tps
- Context
- 203K
- $/Mtok
- $0.400 / $1.75
deepinfra/fp4fp4 - Novita95.65%Degraded24h 93.68%
- 7d
- 94.13%
- 30d
- 94.13%
- p50
- 2.01s
- p99
- 41.2s
- Throughput
- 17 tps
- Context
- 205K
- $/Mtok
- $0.540 / $1.98
novita/fp8fp8 - Z.AI94.79%Degraded24h 92.11%
- 7d
- 91.29%
- 30d
- 91.29%
- p50
- 3.08s
- p99
- 40.5s
- Throughput
- 21 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.20
z-ai/fp4fp4 - AtlasCloud93.83%Degraded24h 90.61%
- 7d
- 94.32%
- 30d
- 94.32%
- p50
- 1.91s
- p99
- 23.0s
- Throughput
- 26 tps
- Context
- 203K
- $/Mtok
- $0.520 / $1.85
atlas-cloud/fp8fp8 - StreamLake92.21%Degraded24h 92.91%
- 7d
- 92.86%
- 30d
- 92.86%
- p50
- 1.99s
- p99
- 25.4s
- Throughput
- 21 tps
- Context
- 200K
- $/Mtok
- $0.480 / $1.76
streamlake/fp8fp8
Measured 4m 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.