GLM 4.5V
z-ai/glm-4.5v
Compare with GLM 4.5 Air, GLM 4.5, GLM 4.6
CompareGLM 4.5V
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Novitanovita/fp8fp8 | No data | — | 97.92% | 2.00s | 6.03s | 58 tps | 66K | $0.600 / $1.80 |
Z.AIz-ai/fp8fp8 | No data | — | 96.27% | 2.39s | 10.4s | 52 tps | 66K | $0.600 / $1.80 |
- Novita—No data24h 97.92%
- p50
- 2.00s
- p99
- 6.03s
- Throughput
- 58 tps
- Context
- 66K
- $/Mtok
- $0.600 / $1.80
novita/fp8fp8 - Z.AI—No data24h 96.27%
- p50
- 2.39s
- p99
- 10.4s
- Throughput
- 52 tps
- Context
- 66K
- $/Mtok
- $0.600 / $1.80
z-ai/fp8fp8
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are omitted from the charts.
No endpoints with data to chart.