Inference provider
Moonshot AI
4 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
4
Median output speed
81 t/s
Median latency
735ms
Median price / 1M
$1.27
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
- Kimi K3Moonshot AI59.7
- Kimi K2.6Moonshot AI45.1
- Kimi K2.7 CodeMoonshot AI43.0
- Kimi K2.5Moonshot AI36.0
View as table
| Model | Intelligence |
|---|---|
| Kimi K3 (Moonshot AI) | 59.7 |
| Kimi K2.6 (Moonshot AI) | 45.1 |
| Kimi K2.7 Code (Moonshot AI) | 43.0 |
| Kimi K2.5 (Moonshot AI) | 36.0 |
Fastest output
Median tokens per second
- Kimi K2.7 CodeMoonshot AI140 t/s
- Kimi K2.6Moonshot AI89 t/s
- Kimi K2.5Moonshot AI73 t/s
- Kimi K3Moonshot AI71 t/s
View as table
| Model | Tokens/s |
|---|---|
| Kimi K2.7 Code (Moonshot AI) | 140 |
| Kimi K2.6 (Moonshot AI) | 89 |
| Kimi K2.5 (Moonshot AI) | 73 |
| Kimi K3 (Moonshot AI) | 71 |
Full catalogue
All 4 models on Moonshot AI
Filter by creator
4 of 4 models| Kimi K3 Moonshot AIopen | 59.7 | $1.35 |
| Kimi K2.6 Moonshot AIopen | 45.1 | $0.23 |
| Kimi K2.7 Code Moonshot AIopen | 43.0 | $0.32 |
| Kimi K2.5 Moonshot AIopen | 36.0 | $0.26 |