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 | No data | — | — | 97.65% | 97.65% | — | — | — | 203K | $1.00 / $3.20 |
| No data | — | — | 99.82% | 99.82% | — | — | — | 203K | $0.950 / $3.15 | |
| No data | — | — | 99.87% | 99.87% | — | — | — | 203K | $0.700 / $2.24 | |
| No data | — | — | 99.41% | 99.41% | — | — | — | 203K | $0.600 / $2.08◆ (best) | |
DigitalOceandigitalocean | No data | — | — | 93.73% | 93.73% | — | — | — | 64K | $1.00 / $3.20 |
| No data | — | — | 99.59% | 99.59% | — | — | — | 203K | $0.600 / $1.92◆ (best) | |
| No data | — | — | 99.99%◆ (best) | 99.99%◆ (best) | — | — | — | 203K | $1.00 / $3.20 | |
| No data | — | — | 99.71% | 99.71% | — | — | — | 205K | $0.950 / $2.55 | |
| No data | — | — | 99.95% | 99.95% | — | — | — | 198K | $0.600 / $1.92◆ (best) | |
| No data | — | — | 93.80% | 93.80% | — | — | — | 198K | $1.00 / $3.20 | |
| No data | — | — | 99.87% | 99.87% | — | — | — | 203K | $1.00 / $3.20 |
- No data24h —
- 7d
- 97.65%
- 30d
- 97.65%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
amazon-bedrock - No data24h —
- 7d
- 99.82%
- 30d
- 99.82%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $0.950 / $3.15
atlas-cloud/fp8fp8 - No data24h —
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $0.700 / $2.24
baidu/fp8fp8 - No data24h —
- 7d
- 99.41%
- 30d
- 99.41%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $0.600 / $2.08◆ (best)
deepinfra/fp4fp4 - No data24h —
- 7d
- 93.73%
- 30d
- 93.73%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 64K
- $/Mtok
- $1.00 / $3.20
digitalocean - No data24h —
- 7d
- 99.59%
- 30d
- 99.59%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $0.600 / $1.92◆ (best)
gmicloud/fp8fp8 - No data24h —
- 7d
- 99.99%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
novita/fp8fp8 - No data24h —
- 7d
- 99.71%
- 30d
- 99.71%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 205K
- $/Mtok
- $0.950 / $2.55
siliconflow/fp8fp8 - No data24h —
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 198K
- $/Mtok
- $0.600 / $1.92◆ (best)
streamlake/fp8fp8 - No data24h —
- 7d
- 93.80%
- 30d
- 93.80%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 198K
- $/Mtok
- $1.00 / $3.20
venice/fp8fp8 - Z.AI—No data24h —
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $1.00 / $3.20
z-ai/fp8fp8
No recent measurement. ◆ marks the best value in each column among these endpoints.
Price vs latency
No endpoint currently reports both a price and a latency.
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.