GLM 4.7
z-ai/glm-4.7
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/fp4fp4 | Healthy | 100% | 98.90% | 1.06s | 8.03s | 23 tps | 203K | $0.400 / $1.75 |
Googlegoogle-vertex | Healthy | 100% | 99.90% | 494ms | 9.77s | 97 tps | 200K | $0.600 / $2.20 |
Mancer 2mancer/fp4fp4 | Healthy | 100% | 96.45% | 1.28s | 9.08s | 17 tps | 131K | $0.600 / $2.50 |
Venicevenice/fp4fp4 | Healthy | 100% | 98.01% | 1.44s | 5.88s | 23 tps | 198K | $0.550 / $2.65 |
AtlasCloudatlas-cloud/fp8fp8 | Degraded | 97.83% | 96.92% | 1.94s | 24.6s | 27 tps | 203K | $0.520 / $1.85 |
Novitanovita/fp8fp8 | Degraded | 93.52% | 93.56% | 2.39s | 35.5s | 24 tps | 205K | $0.540 / $1.98 |
StreamLakestreamlake/fp8fp8 | Degraded | 93.15% | 92.38% | 1.96s | 25.1s | 30 tps | 200K | $0.480 / $1.76 |
Z.AIz-ai/fp4fp4 | Down | 88.66% | 82.45% | 16.0s | 39.4s | 26 tps | 203K | $0.600 / $2.20 |
- DeepInfra100%Healthy24h 98.90%
- p50
- 1.06s
- p99
- 8.03s
- Throughput
- 23 tps
- Context
- 203K
- $/Mtok
- $0.400 / $1.75
deepinfra/fp4fp4 - Google100%Healthy24h 99.90%
- p50
- 494ms
- p99
- 9.77s
- Throughput
- 97 tps
- Context
- 200K
- $/Mtok
- $0.600 / $2.20
google-vertex - Mancer 2100%Healthy24h 96.45%
- p50
- 1.28s
- p99
- 9.08s
- Throughput
- 17 tps
- Context
- 131K
- $/Mtok
- $0.600 / $2.50
mancer/fp4fp4 - Venice100%Healthy24h 98.01%
- p50
- 1.44s
- p99
- 5.88s
- Throughput
- 23 tps
- Context
- 198K
- $/Mtok
- $0.550 / $2.65
venice/fp4fp4 - AtlasCloud97.83%Degraded24h 96.92%
- p50
- 1.94s
- p99
- 24.6s
- Throughput
- 27 tps
- Context
- 203K
- $/Mtok
- $0.520 / $1.85
atlas-cloud/fp8fp8 - Novita93.52%Degraded24h 93.56%
- p50
- 2.39s
- p99
- 35.5s
- Throughput
- 24 tps
- Context
- 205K
- $/Mtok
- $0.540 / $1.98
novita/fp8fp8 - StreamLake93.15%Degraded24h 92.38%
- p50
- 1.96s
- p99
- 25.1s
- Throughput
- 30 tps
- Context
- 200K
- $/Mtok
- $0.480 / $1.76
streamlake/fp8fp8 - Z.AI88.66%Down24h 82.45%
- p50
- 16.0s
- p99
- 39.4s
- Throughput
- 26 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.20
z-ai/fp4fp4
Measured 2m 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.
Throughput
Median tokens per second.