Inference provider
Z.AI
11 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
11
Median output speed
42 t/s
Median latency
937ms
Median price / 1M
$1
Catalogue
Strongest and fastest on this provider
What the catalogue looks like at the top end, on the two axes that usually decide the choice.
Highest Intelligence Index
Among models this provider serves
- GLM 5.2Z.ai52.6
- GLM 5.1Z.ai41.0
- GLM 5Z.ai40.6
- GLM 5 TurboZ.ai39.1
- GLM 5V TurboZ.ai35.3
- GLM 4.7Z.ai34.5
- GLM 4.6Z.ai23.4
- GLM 4.5Z.ai19.7
- GLM 4.5 AirZ.ai16.7
- GLM 4.6VZ.ai10.9
View as table
| Model | Intelligence |
|---|---|
| GLM 5.2 (Z.ai) | 52.6 |
| GLM 5.1 (Z.ai) | 41.0 |
| GLM 5 (Z.ai) | 40.6 |
| GLM 5 Turbo (Z.ai) | 39.1 |
| GLM 5V Turbo (Z.ai) | 35.3 |
| GLM 4.7 (Z.ai) | 34.5 |
| GLM 4.6 (Z.ai) | 23.4 |
| GLM 4.5 (Z.ai) | 19.7 |
| GLM 4.5 Air (Z.ai) | 16.7 |
| GLM 4.6V (Z.ai) | 10.9 |
Fastest output
Median tokens per second
- GLM 4.7Z.ai502 t/s
- GLM 5.2Z.ai142 t/s
- GLM 5.1Z.ai67 t/s
- GLM 4.6Z.ai56 t/s
- GLM 5Z.ai48 t/s
- GLM 4.5 AirZ.ai42 t/s
- GLM 4.5VZ.ai42 t/s
- GLM 4.5Z.ai39 t/s
- GLM 5V TurboZ.ai37 t/s
- GLM 4.6VZ.ai20 t/s
View as table
| Model | Tokens/s |
|---|---|
| GLM 4.7 (Z.ai) | 502 |
| GLM 5.2 (Z.ai) | 142 |
| GLM 5.1 (Z.ai) | 67 |
| GLM 4.6 (Z.ai) | 56 |
| GLM 5 (Z.ai) | 48 |
| GLM 4.5 Air (Z.ai) | 42 |
| GLM 4.5V (Z.ai) | 42 |
| GLM 4.5 (Z.ai) | 39 |
| GLM 5V Turbo (Z.ai) | 37 |
| GLM 4.6V (Z.ai) | 20 |
Full catalogue
All 11 models on Z.AI
Filter by creator
11 of 11 models| GLM 5.2 Z.aiopen | 52.6 | $0.23 |
| GLM 5.1 Z.aiopen | 41.0 | $0.29 |
| GLM 5 Z.aiopen | 40.6 | $0.25 |
| GLM 5 Turbo Z.ai | 39.1 | $0.38 |
| GLM 5V Turbo Z.ai | 35.3 | $0.38 |
| GLM 4.7 Z.aiopen | 34.5 | $0.16 |
| GLM 4.6 Z.aiopen | 23.4 | $0.18 |
| GLM 4.5 Z.aiopen | 19.7 | $0.21 |
| GLM 4.5 Air Z.aiopen | 16.7 | $0.07 |
| GLM 4.6V Z.aiopen | 10.9 | $0.09 |
| GLM 4.5V Z.aiopen | 6.8 | $0.17 |