GLM 4.7 Flash
z-ai/glm-4.7-flash
CompareGLM 4.7 Flash
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/bf16bf16 | Healthy | 100% | 99.54% | 412ms | 12.1s | 24 tps | 203K | $0.060 / $0.400 |
Venicevenice/fp8fp8 | Healthy | 100% | 97.97% | 653ms | 5.58s | 32 tps | 128K | $0.060 / $0.400 |
Cloudflarecloudflare | Healthy | 98.47% | 98.03% | 369ms | 8.40s | 29 tps | 131K | $0.061 / $0.400 |
Novitanovita/bf16bf16 | Degraded | 90.00% | 93.26% | 1.25s | 85.6s | 28 tps | 200K | $0.070 / $0.400 |
- DeepInfra100%Healthy24h 99.54%
- p50
- 412ms
- p99
- 12.1s
- Throughput
- 24 tps
- Context
- 203K
- $/Mtok
- $0.060 / $0.400
deepinfra/bf16bf16 - Venice100%Healthy24h 97.97%
- p50
- 653ms
- p99
- 5.58s
- Throughput
- 32 tps
- Context
- 128K
- $/Mtok
- $0.060 / $0.400
venice/fp8fp8 - Cloudflare98.47%Healthy24h 98.03%
- p50
- 369ms
- p99
- 8.40s
- Throughput
- 29 tps
- Context
- 131K
- $/Mtok
- $0.061 / $0.400
cloudflare - Novita90.00%Degraded24h 93.26%
- p50
- 1.25s
- p99
- 85.6s
- Throughput
- 28 tps
- Context
- 200K
- $/Mtok
- $0.070 / $0.400
novita/bf16bf16
Measured 5m 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.