Inference provider
Nvidia
7 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
7
Median output speed
32 t/s
Median latency
1.05s
Median price / 1M
Free
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
- 15.0
View as table
| Model | Intelligence |
|---|---|
| Nemotron 3 Nano Omni (free) (NVIDIA) | 15.0 |
Fastest output
Median tokens per second
- 101 t/s
- 94 t/s
- 75 t/s
- 32 t/s
- Nemotron 3 Super (free)NVIDIA26 t/s
- Nemotron 3 Ultra (free)NVIDIA22 t/s
- 22 t/s
View as table
| Model | Tokens/s |
|---|---|
| Nemotron 3 Nano Omni (free) (NVIDIA) | 101 |
| Nemotron 3 Nano 30B A3B (free) (NVIDIA) | 94 |
| Nemotron 3.5 Content Safety (free) (NVIDIA) | 75 |
| Nemotron Nano 9B V2 (free) (NVIDIA) | 32 |
| Nemotron 3 Super (free) (NVIDIA) | 26 |
| Nemotron 3 Ultra (free) (NVIDIA) | 22 |
| Nemotron Nano 12B 2 VL (free) (NVIDIA) | 22 |
Full catalogue
All 7 models on Nvidia
Filter by creator
7 of 7 models| Nemotron 3 Nano Omni (free) NVIDIAopen | 15.0 | Free |
| Nemotron 3.5 Content Safety (free) NVIDIAopen | — | Free |
| Nemotron 3 Ultra (free) NVIDIAopen | — | Free |
| Nemotron 3 Super (free) NVIDIAopen | — | Free |
| Nemotron 3 Nano 30B A3B (free) NVIDIAopen | — | Free |
| Nemotron Nano 12B 2 VL (free) NVIDIAopen | — | Free |
| Nemotron Nano 9B V2 (free) NVIDIAopen | — | Free |