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 |
|---|---|---|---|---|---|---|---|---|
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 96.91% | 1.98s | 21.7s | 36 tps | 203K | $0.520 / $1.85 |
Googlegoogle-vertex | Healthy | 100% | 99.88% | 471ms | 9.50s | 96 tps | 200K | $0.600 / $2.20 |
Venicevenice/fp4fp4 | Healthy | 100% | 98.06% | 1.75s | 18.7s | 17 tps | 198K | $0.550 / $2.65 |
DeepInfradeepinfra/fp4fp4 | Healthy | 99.77% | 98.95% | 1.39s | 19.5s | 17 tps | 203K | $0.400 / $1.75 |
Novitanovita/fp8fp8 | Healthy | 98.44% | 93.46% | 2.00s | 31.0s | 26 tps | 205K | $0.540 / $1.98 |
Mancer 2mancer/fp4fp4 | Healthy | 98.41% | 96.67% | 1.44s | 12.3s | 14 tps | 131K | $0.600 / $2.50 |
StreamLakestreamlake/fp8fp8 | Healthy | 97.46% | 92.41% | 1.64s | 18.3s | 27 tps | 200K | $0.480 / $1.76 |
Z.AIz-ai/fp4fp4 | Degraded | 93.33% | 84.84% | 13.9s | 31.8s | 31 tps | 203K | $0.600 / $2.20 |
- AtlasCloud100%Healthy24h 96.91%
- p50
- 1.98s
- p99
- 21.7s
- Throughput
- 36 tps
- Context
- 203K
- $/Mtok
- $0.520 / $1.85
atlas-cloud/fp8fp8 - Google100%Healthy24h 99.88%
- p50
- 471ms
- p99
- 9.50s
- Throughput
- 96 tps
- Context
- 200K
- $/Mtok
- $0.600 / $2.20
google-vertex - Venice100%Healthy24h 98.06%
- p50
- 1.75s
- p99
- 18.7s
- Throughput
- 17 tps
- Context
- 198K
- $/Mtok
- $0.550 / $2.65
venice/fp4fp4 - DeepInfra99.77%Healthy24h 98.95%
- p50
- 1.39s
- p99
- 19.5s
- Throughput
- 17 tps
- Context
- 203K
- $/Mtok
- $0.400 / $1.75
deepinfra/fp4fp4 - Novita98.44%Healthy24h 93.46%
- p50
- 2.00s
- p99
- 31.0s
- Throughput
- 26 tps
- Context
- 205K
- $/Mtok
- $0.540 / $1.98
novita/fp8fp8 - Mancer 298.41%Healthy24h 96.67%
- p50
- 1.44s
- p99
- 12.3s
- Throughput
- 14 tps
- Context
- 131K
- $/Mtok
- $0.600 / $2.50
mancer/fp4fp4 - StreamLake97.46%Healthy24h 92.41%
- p50
- 1.64s
- p99
- 18.3s
- Throughput
- 27 tps
- Context
- 200K
- $/Mtok
- $0.480 / $1.76
streamlake/fp8fp8 - Z.AI93.33%Degraded24h 84.84%
- p50
- 13.9s
- p99
- 31.8s
- Throughput
- 31 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, averaged over the hour.
Throughput
Median tokens per second.