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) | 99.89% | 99.87% | 99.87% | 1.18s | 12.3s | 40 tps | 203K | $0.700 / $2.24 | |
| Healthy | 100%◆ (best) | 99.84% | 99.41% | 99.41% | 828ms | 39.5s | 26 tps | 203K | $0.600 / $2.08◆ (best) | |
| Healthy | 100%◆ (best) | 99.93% | 99.95% | 99.95% | 2.47s | 6.04s | 46 tps | 198K | $0.600 / $1.92◆ (best) | |
| Healthy | 100%◆ (best) | 99.98% | 99.87% | 99.87% | 944ms | 4.25s◆ (best) | 63 tps | 203K | $1.00 / $3.20 | |
| Healthy | 98.88% | 99.75% | 99.59% | 99.59% | 1.13s | 4.56s | 52 tps | 203K | $0.600 / $1.92◆ (best) | |
Amazon Bedrockamazon-bedrock | No data | — | 96.21% | 97.65% | 97.65% | 751ms◆ (best) | 5.89s | 8.5 tps | 203K | $1.00 / $3.20 |
| No data | — | 99.80% | 99.82% | 99.82% | 1.98s | 22.0s | 39 tps | 203K | $0.950 / $3.15 | |
DigitalOceandigitalocean | No data | — | 96.04% | 93.73% | 93.73% | 1.49s | 9.89s | 7.0 tps | 64K | $1.00 / $3.20 |
| No data | — | 99.97% | 99.99%◆ (best) | 99.99%◆ (best) | 2.29s | 8.09s | 64 tps◆ (best) | 203K | $1.00 / $3.20 | |
| No data | — | 99.84% | 99.71% | 99.71% | 2.39s | 10.5s | 38 tps | 205K | $0.950 / $2.55 | |
| No data | — | 96.17% | 93.80% | 93.80% | 1.14s | 4.81s | 31 tps | 198K | $1.00 / $3.20 |
- Baidu100%◆ (best)Healthy24h 99.89%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 1.18s
- p99
- 12.3s
- Throughput
- 40 tps
- Context
- 203K
- $/Mtok
- $0.700 / $2.24
baidu/fp8fp8 - DeepInfra100%◆ (best)Healthy24h 99.84%
- 7d
- 99.41%
- 30d
- 99.41%
- p50
- 828ms
- p99
- 39.5s
- Throughput
- 26 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.08◆ (best)
deepinfra/fp4fp4 - StreamLake100%◆ (best)Healthy24h 99.93%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 2.47s
- p99
- 6.04s
- Throughput
- 46 tps
- Context
- 198K
- $/Mtok
- $0.600 / $1.92◆ (best)
streamlake/fp8fp8 - Z.AI100%◆ (best)Healthy24h 99.98%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 944ms
- p99
- 4.25s◆ (best)
- Throughput
- 63 tps
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
z-ai/fp8fp8 - GMICloud98.88%Healthy24h 99.75%
- 7d
- 99.59%
- 30d
- 99.59%
- p50
- 1.13s
- p99
- 4.56s
- Throughput
- 52 tps
- Context
- 203K
- $/Mtok
- $0.600 / $1.92◆ (best)
gmicloud/fp8fp8 - No data24h 96.21%
- 7d
- 97.65%
- 30d
- 97.65%
- p50
- 751ms◆ (best)
- p99
- 5.89s
- Throughput
- 8.5 tps
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
amazon-bedrock - No data24h 99.80%
- 7d
- 99.82%
- 30d
- 99.82%
- p50
- 1.98s
- p99
- 22.0s
- Throughput
- 39 tps
- Context
- 203K
- $/Mtok
- $0.950 / $3.15
atlas-cloud/fp8fp8 - No data24h 96.04%
- 7d
- 93.73%
- 30d
- 93.73%
- p50
- 1.49s
- p99
- 9.89s
- Throughput
- 7.0 tps
- Context
- 64K
- $/Mtok
- $1.00 / $3.20
digitalocean - No data24h 99.97%
- 7d
- 99.99%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- 2.29s
- p99
- 8.09s
- Throughput
- 64 tps◆ (best)
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
novita/fp8fp8 - No data24h 99.84%
- 7d
- 99.71%
- 30d
- 99.71%
- p50
- 2.39s
- p99
- 10.5s
- Throughput
- 38 tps
- Context
- 205K
- $/Mtok
- $0.950 / $2.55
siliconflow/fp8fp8 - No data24h 96.17%
- 7d
- 93.80%
- 30d
- 93.80%
- p50
- 1.14s
- p99
- 4.81s
- Throughput
- 31 tps
- Context
- 198K
- $/Mtok
- $1.00 / $3.20
venice/fp8fp8
Measured 59s 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.
Throughput
Median tokens per second.