Inference provider
xAI
5 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
5
Median output speed
93 t/s
Median latency
925ms
Median price / 1M
$1.56
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
View as table
| Model | Intelligence |
|---|---|
| Grok 4.5 (xAI) | 55.8 |
| Grok 4.20 (xAI) | 38.0 |
| Grok 4.3 (xAI) | 37.9 |
Fastest output
Median tokens per second
View as table
| Model | Tokens/s |
|---|---|
| Grok 4.20 Multi-Agent (xAI) | 337 |
| Grok 4.3 (xAI) | 93 |
| Grok 4.20 (xAI) | 93 |
| Grok Build 0.1 (xAI) | 85 |
| Grok 4.5 (xAI) | 52 |
Full catalogue
All 5 models on xAI
Filter by creator
5 of 5 models| Grok 4.5 xAI | 55.8 | $0.58 |
| Grok 4.20 xAI | 38.0 | $0.26 |
| Grok 4.3 xAI | 37.9 | $0.26 |
| Grok Build 0.1 xAI | — | $0.21 |
| Grok 4.20 Multi-Agent xAI | — | $0.26 |