Nemotron 3 Super 120B A12B
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
1M
tokens
Offers
10
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Showing free/$0 offers. Hide them.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestnemotron-3-super-120b-a12b | Kenari | $0 | $0 | $0 | 262K |
| models.devnvidia/nemotron-3-super-120b-a12b | NanoGPT | $0.05 | $0.25 | $0 | 262K |
| models.devnvidia/nemotron-3-super-120b-a12b | Kilo Gateway | $0.085 | $0.4 | $0 | 262K |
| OpenRouternvidia/nemotron-3-super-120b-a12b | OpenRouter | $0.085 | $0.4 | $0 | 1M |
| models.devnvidia/nemotron-3-super-120b-a12b | Vercel AI Gateway | $0.15 | $0.65 | $0 | 256K |
| models.devnvidia/nemotron-3-super-120b-a12b | NVIDIA | $0.2 | $0.8 | $0 | 262K |
| models.devnvidia/nemotron-3-super-120b-a12b | Perplexity | $0.25 | $2.50 | $0 | 1M |
| models.devnemotron-3-super-120b-a12b | Cortecs | $0.266 | $0.799 | $0 | 262K |
| models.devnvidia/nemotron-3-super-120b-a12b | Nebius | $0.3 | $0.9 | $0 | 256K |
| models.devnvidia/nemotron-3-super-120b-a12b | TensorX | $0.3 | $0.9 | $0.075 | 262K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2026-02Released: 2026-03-11Family: nemotron
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence25.4
- AA coding37.7
- AA agentic8.7
Sources: Arena AI, Artificial Analysis. See /benchmarks.