GLM 4.7
z-ai/glm-4.7
Compare with GLM 4.7 Flash, GLM 4.6, GLM 4.6V
CompareGLM 4.7
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex | Healthy | 100% | 99.83% | 534ms | 12.4s | 113 tps | 200K | $0.600 / $2.20 |
Mancer 2mancer/fp4fp4 | Healthy | 100% | 97.06% | 1.31s | 16.7s | 14 tps | 131K | $0.600 / $2.50 |
Venicevenice/fp4fp4 | Healthy | 100% | 98.39% | 1.50s | 18.6s | 15 tps | 198K | $0.550 / $2.65 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 99.76% | 96.84% | 2.03s | 18.4s | 42 tps | 203K | $0.520 / $1.85 |
StreamLakestreamlake/fp8fp8 | Healthy | 98.84% | 92.34% | 2.63s | 32.3s | 40 tps | 200K | $0.480 / $1.76 |
DeepInfradeepinfra/fp4fp4 | Healthy | 97.04% | 99.05% | 1.29s | 22.1s | 16 tps | 203K | $0.400 / $1.75 |
Novitanovita/fp8fp8 | Degraded | 94.52% | 93.33% | 2.58s | 31.1s | 27 tps | 205K | $0.540 / $1.98 |
Z.AIz-ai/fp4fp4 | Degraded | 90.69% | 88.93% | 13.0s | 32.8s | 35 tps | 203K | $0.600 / $2.20 |
- Google100%Healthy24h 99.83%
- p50
- 534ms
- p99
- 12.4s
- Throughput
- 113 tps
- Context
- 200K
- $/Mtok
- $0.600 / $2.20
google-vertex - Mancer 2100%Healthy24h 97.06%
- p50
- 1.31s
- p99
- 16.7s
- Throughput
- 14 tps
- Context
- 131K
- $/Mtok
- $0.600 / $2.50
mancer/fp4fp4 - Venice100%Healthy24h 98.39%
- p50
- 1.50s
- p99
- 18.6s
- Throughput
- 15 tps
- Context
- 198K
- $/Mtok
- $0.550 / $2.65
venice/fp4fp4 - AtlasCloud99.76%Healthy24h 96.84%
- p50
- 2.03s
- p99
- 18.4s
- Throughput
- 42 tps
- Context
- 203K
- $/Mtok
- $0.520 / $1.85
atlas-cloud/fp8fp8 - StreamLake98.84%Healthy24h 92.34%
- p50
- 2.63s
- p99
- 32.3s
- Throughput
- 40 tps
- Context
- 200K
- $/Mtok
- $0.480 / $1.76
streamlake/fp8fp8 - DeepInfra97.04%Healthy24h 99.05%
- p50
- 1.29s
- p99
- 22.1s
- Throughput
- 16 tps
- Context
- 203K
- $/Mtok
- $0.400 / $1.75
deepinfra/fp4fp4 - Novita94.52%Degraded24h 93.33%
- p50
- 2.58s
- p99
- 31.1s
- Throughput
- 27 tps
- Context
- 205K
- $/Mtok
- $0.540 / $1.98
novita/fp8fp8 - Z.AI90.69%Degraded24h 88.93%
- p50
- 13.0s
- p99
- 32.8s
- Throughput
- 35 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.20
z-ai/fp4fp4
Measured 53s 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.