Models20in catalog
Largest context1MNemotron 3 Ultra
Avg context
281K
Cheapest input
$0.040/M
Nvidia Nemotron Nano 9b
Largest output
262K
Nemotron 3 Super (free)
Speed tiers
balanced 8fast 11deep 1
Capabilities
What Nvidia models support across the catalog.
Vision
5 / 20
25% of models
Tool use
16 / 20
80% of models
Function calling
16 / 20
80% of models
Extended thinking
15 / 20
75% of models
Streaming
20 / 20
100% of models
Prompt caching
3 / 20
15% of models
All Nvidia models
Sorted by context window, largest first. Tap a row for full specs.
| Model | Context | Max output | Input $/M | Speed |
|---|---|---|---|---|
| Nemotron 3 Ultra | 1M | 16K | — | balanced |
| Nemotron 3 Ultra (free) | 1M | 66K | — | balanced |
| Nemotron 3 Ultra (batch) | 512K | — | — | balanced |
| Nemotron 3 Nano 30B A3B | 262K | — | — | fast |
| Nemotron 3 Super | 262K | — | — | balanced |
| Nemotron 3 Super (free) | 262K | 262K | — | balanced |
| Nvidia Nemotron Nano 3 30b | 262K | 8K | $0.060/M | fast |
| Nemotron 3 120b A12b | 256K | 256K | $0.500/M | balanced |
| Nemotron 3 Nano 30B A3B (free) | 256K | — | — | fast |
| Nemotron 3 Nano Omni (free) | 256K | 66K | — | fast |
| Nvidia Nemotron Super 3 120b | 256K | 33K | $0.150/M | balanced |
| Llama 3.1 Nemotron 70B InstructLlama 3.1 | 131K | 16K | — | deep |
| Nemotron Nano 12B 2 VL | 131K | — | — | fast |
| Nemotron Nano 9B V2 | 131K | — | — | fast |
| Nvidia Nemotron Nano 9b | 131K | 131K | $0.040/M | fast |
| Nemotron 3.5 Content Safety (free) | 128K | 8K | — | balanced |
| Nemotron Nano 12B 2 VL (free) | 128K | 128K | — | fast |
| Nemotron Nano 9B V2 (free) | 128K | — | — | fast |
| Nvidia Nemotron Nano 12b | 128K | 8K | $0.200/M | fast |
| Nemotron Nano V2 12b Vl | 4K | 4K | $0.100/M | fast |
See rankings
How Nvidia models rank against the full catalog.