NVIDIA
Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b
Input
$0.30
per 1M tokens
Output
$2.40
per 1M tokens
Cached input
$0.15
per 1M tokens
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
- Released
- Context window
- 262K tokens
- Max output
- 236K tokens
- Input
- text
- Output
- text
- Reasoning
- Yes
Price history
- input $0.08 → $0.30 +275% · output $0.45 → $2.40 +433%
- input $0.30 → $0.08 -73% · output $2.40 → $0.45 -81%
Providers on OpenRouter
3 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| DeepInfrabf16 | $0.085 | $0.40 | 262K | 100% | 100% |
| DekaLLMfp8 | $0.08 | $0.45 | 262K | 100% | 99.65% |
| Crusoefp8 | $0.30 | $2.40 | 262K | 100% | 100% |