GLM 5: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.84% | 99.54% | 99.61% | 1.13s | 6.06s | 59 tps | 203K | $0.700 / $2.24 | |
| Degraded | 100%◆ (best) | 99.49% | 99.46% | 98.49% | 3.60s | 9.49s | 41 tps | 203K | $0.600 / $1.92◆ (best) | |
| Healthy | 100%◆ (best) | 99.98% | 99.99%◆ (best) | 99.97%◆ (best) | 1.68s | 11.2s | 44 tps | 203K | $1.00 / $3.20 | |
| Healthy | 100%◆ (best) | 99.54% | 99.57% | 99.50% | 3.07s | 10.3s | 31 tps | 205K | $0.950 / $2.55 | |
| Healthy | 100%◆ (best) | 99.86% | 99.83% | 99.75% | 3.14s | 9.19s | 37 tps | 198K | $0.600 / $1.92◆ (best) | |
| Healthy | 100%◆ (best) | 99.94% | 99.95% | 99.93% | 7.93s | 21.8s | 48 tps | 203K | $1.00 / $3.20 | |
Amazon Bedrockamazon-bedrock | No data | — | 98.85% | 99.69% | 97.96% | 773ms◆ (best) | 4.00s◆ (best) | 115 tps◆ (best) | 203K | $1.00 / $3.20 |
| No data | — | — | — | — | — | — | — | 203K | $0.950 / $3.15 | |
| No data | — | — | — | 99.92% | — | — | — | 203K | $0.600 / $2.08◆ (best) | |
DigitalOceandigitalocean | No data | — | — | — | 97.66% | — | — | — | 64K | $1.00 / $3.20 |
| No data | — | 98.20% | 99.11% | 98.65% | 1.38s | 10.5s | 58 tps | 198K | $1.00 / $3.20 |
- Baidu100%◆ (best)Healthy24h 99.84%
- 7d
- 99.54%
- 30d
- 99.61%
- p50
- 1.13s
- p99
- 6.06s
- Throughput
- 59 tps
- Context
- 203K
- $/Mtok
- $0.700 / $2.24
baidu/fp8fp8 - GMICloud100%◆ (best)Degraded24h 99.49%
- 7d
- 99.46%
- 30d
- 98.49%
- p50
- 3.60s
- p99
- 9.49s
- Throughput
- 41 tps
- Context
- 203K
- $/Mtok
- $0.600 / $1.92◆ (best)
gmicloud/fp8fp8 - Novita100%◆ (best)Healthy24h 99.98%
- 7d
- 99.99%◆ (best)
- 30d
- 99.97%◆ (best)
- p50
- 1.68s
- p99
- 11.2s
- Throughput
- 44 tps
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
novita/fp8fp8 - SiliconFlow100%◆ (best)Healthy24h 99.54%
- 7d
- 99.57%
- 30d
- 99.50%
- p50
- 3.07s
- p99
- 10.3s
- Throughput
- 31 tps
- Context
- 205K
- $/Mtok
- $0.950 / $2.55
siliconflow/fp8fp8 - StreamLake100%◆ (best)Healthy24h 99.86%
- 7d
- 99.83%
- 30d
- 99.75%
- p50
- 3.14s
- p99
- 9.19s
- Throughput
- 37 tps
- Context
- 198K
- $/Mtok
- $0.600 / $1.92◆ (best)
streamlake/fp8fp8 - Z.AI100%◆ (best)Healthy24h 99.94%
- 7d
- 99.95%
- 30d
- 99.93%
- p50
- 7.93s
- p99
- 21.8s
- Throughput
- 48 tps
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
z-ai/fp8fp8 - No data24h 98.85%
- 7d
- 99.69%
- 30d
- 97.96%
- p50
- 773ms◆ (best)
- p99
- 4.00s◆ (best)
- Throughput
- 115 tps◆ (best)
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
amazon-bedrock - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $0.950 / $3.15
atlas-cloud/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.92%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $0.600 / $2.08◆ (best)
deepinfra/fp4fp4 - No data24h —
- 7d
- —
- 30d
- 97.66%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 64K
- $/Mtok
- $1.00 / $3.20
digitalocean - No data24h 98.20%
- 7d
- 99.11%
- 30d
- 98.65%
- p50
- 1.38s
- p99
- 10.5s
- Throughput
- 58 tps
- Context
- 198K
- $/Mtok
- $1.00 / $3.20
venice/fp8fp8
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.