NVIDIA
Nemotron 3 Super
Released 2026-03-11
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...
You send / 1M
$0.080
tokens in
It replies / 1M
$0.450
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0003
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · bf16 | $0.085 | $0.400 | 100% | Read |
| DekaLLM · fp8 | $0.080 | $0.450 | 99% | Read |
| Crusoe · fp8 | $0.300 | $2.40 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 236K tokens
- Intelligence score: 12.8 / 100 (Artificial Analysis)
Similar models
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Reasoning AI ModelsTop No-Training Cheap Tool-Calling AI Models