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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock | Healthy | 100%◆ (best) | 99.23% | 99.68% | 97.89% | 620ms◆ (best) | 3.21s◆ (best) | 119 tps◆ (best) | 203K | $1.00 / $3.20 |
| Healthy | 100%◆ (best) | 99.99% | 99.99%◆ (best) | 99.97%◆ (best) | 1.56s | 9.41s | 49 tps | 203K | $1.00 / $3.20 | |
| Healthy | 100%◆ (best) | 99.62% | 99.57% | 99.42% | 2.38s | 6.57s | 44 tps | 205K | $0.950 / $2.55 | |
| Healthy | 100%◆ (best) | 99.96% | 99.95% | 99.93% | 6.97s | 10.5s | 54 tps | 203K | $1.00 / $3.20 | |
| Healthy | 99.70% | 99.87% | 99.80% | 99.74% | 2.20s | 6.46s | 53 tps | 198K | $0.600 / $1.92◆ (best) | |
| Healthy | 95.56% | 99.53% | 99.40% | 98.48% | 2.50s | 6.45s | 57 tps | 203K | $0.600 / $1.92◆ (best) | |
| Degraded | 93.02% | 99.62% | 99.53% | 99.62% | 1.61s | 15.0s | 54 tps | 203K | $0.700 / $2.24 | |
| No data | — | — | — | — | — | — | — | 203K | $0.950 / $3.15 | |
| No data | — | — | — | 99.89% | — | — | — | 203K | $0.600 / $2.08◆ (best) | |
DigitalOceandigitalocean | No data | — | — | — | 97.82% | — | — | — | 64K | $1.00 / $3.20 |
| No data | — | 98.55% | 99.03% | 98.68% | 1.19s | 9.84s | 47 tps | 198K | $1.00 / $3.20 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.23%
- 7d
- 99.68%
- 30d
- 97.89%
- p50
- 620ms◆ (best)
- p99
- 3.21s◆ (best)
- Throughput
- 119 tps◆ (best)
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
amazon-bedrock - Novita100%◆ (best)Healthy24h 99.99%
- 7d
- 99.99%◆ (best)
- 30d
- 99.97%◆ (best)
- p50
- 1.56s
- p99
- 9.41s
- Throughput
- 49 tps
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
novita/fp8fp8 - SiliconFlow100%◆ (best)Healthy24h 99.62%
- 7d
- 99.57%
- 30d
- 99.42%
- p50
- 2.38s
- p99
- 6.57s
- Throughput
- 44 tps
- Context
- 205K
- $/Mtok
- $0.950 / $2.55
siliconflow/fp8fp8 - Z.AI100%◆ (best)Healthy24h 99.96%
- 7d
- 99.95%
- 30d
- 99.93%
- p50
- 6.97s
- p99
- 10.5s
- Throughput
- 54 tps
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
z-ai/fp8fp8 - StreamLake99.70%Healthy24h 99.87%
- 7d
- 99.80%
- 30d
- 99.74%
- p50
- 2.20s
- p99
- 6.46s
- Throughput
- 53 tps
- Context
- 198K
- $/Mtok
- $0.600 / $1.92◆ (best)
streamlake/fp8fp8 - GMICloud95.56%Healthy24h 99.53%
- 7d
- 99.40%
- 30d
- 98.48%
- p50
- 2.50s
- p99
- 6.45s
- Throughput
- 57 tps
- Context
- 203K
- $/Mtok
- $0.600 / $1.92◆ (best)
gmicloud/fp8fp8 - Baidu93.02%Degraded24h 99.62%
- 7d
- 99.53%
- 30d
- 99.62%
- p50
- 1.61s
- p99
- 15.0s
- Throughput
- 54 tps
- Context
- 203K
- $/Mtok
- $0.700 / $2.24
baidu/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $0.950 / $3.15
atlas-cloud/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.89%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $0.600 / $2.08◆ (best)
deepinfra/fp4fp4 - No data24h —
- 7d
- —
- 30d
- 97.82%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 64K
- $/Mtok
- $1.00 / $3.20
digitalocean - No data24h 98.55%
- 7d
- 99.03%
- 30d
- 98.68%
- p50
- 1.19s
- p99
- 9.84s
- Throughput
- 47 tps
- Context
- 198K
- $/Mtok
- $1.00 / $3.20
venice/fp8fp8
Measured 4m 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.