GLM 4.6
z-ai/glm-4.6
Compare with GLM 4.6V, GLM 4.5 Air, GLM 4.5V
CompareGLM 4.6
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 99.78% | 1.34s | 18.0s | 40 tps | 203K | $0.600 / $2.20 |
DeepInfradeepinfra/fp4fp4 | Healthy | 100% | 98.96% | 527ms | 4.16s | 39 tps | 203K | $0.500 / $2.00 |
Venicevenice/fp4fp4 | Healthy | 97.44% | 98.88% | 1.33s | 12.9s | 14 tps | 198K | $0.430 / $1.75 |
Novitanovita/bf16bf16 | Degraded | 93.85% | 97.12% | 1.31s | 17.9s | 42 tps | 205K | $0.550 / $2.20 |
Z.AIz-ai/fp4fp4 | No data | — | 94.39% | 3.52s | 21.9s | 36 tps | 203K | $0.600 / $2.20 |
- AtlasCloud100%Healthy24h 99.78%
- p50
- 1.34s
- p99
- 18.0s
- Throughput
- 40 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.20
atlas-cloud/fp8fp8 - DeepInfra100%Healthy24h 98.96%
- p50
- 527ms
- p99
- 4.16s
- Throughput
- 39 tps
- Context
- 203K
- $/Mtok
- $0.500 / $2.00
deepinfra/fp4fp4 - Venice97.44%Healthy24h 98.88%
- p50
- 1.33s
- p99
- 12.9s
- Throughput
- 14 tps
- Context
- 198K
- $/Mtok
- $0.430 / $1.75
venice/fp4fp4 - Novita93.85%Degraded24h 97.12%
- p50
- 1.31s
- p99
- 17.9s
- Throughput
- 42 tps
- Context
- 205K
- $/Mtok
- $0.550 / $2.20
novita/bf16bf16 - Z.AI—No data24h 94.39%
- p50
- 3.52s
- p99
- 21.9s
- Throughput
- 36 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
1 endpoint reporting no data is 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.