GLM 4.6V
z-ai/glm-4.6v
Compare with GLM 4.6, GLM 4.5 Air, GLM 4.5V
CompareGLM 4.6V
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Novitanovita/bf16bf16 | Healthy | 98.52% | 92.95% | 876ms | 54.7s | 13 tps | 131K | $0.300 / $0.900 |
Z.AIz-ai/fp8fp8 | Degraded | 93.02% | 88.08% | 3.67s | 130s | 28 tps | 131K | $0.300 / $0.900 |
- Novita98.52%Healthy24h 92.95%
- p50
- 876ms
- p99
- 54.7s
- Throughput
- 13 tps
- Context
- 131K
- $/Mtok
- $0.300 / $0.900
novita/bf16bf16 - Z.AI93.02%Degraded24h 88.08%
- p50
- 3.67s
- p99
- 130s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.300 / $0.900
z-ai/fp8fp8
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.