Nemotron 3 Super 120B A12B
SyntheticOpen weights
Nemotron 3 Super 120B A12B by Synthetic costs $0.30 per 1M input tokens and $1.00 per 1M output tokens, with a 262K-token context window.
Pricing
Input (per 1M tokens)
$0.30
Output (per 1M tokens)
$1.00
Cached input (per 1M)
$0.30
Specifications
- Provider
- Synthetic
- Context window
- 262K tokens
- Parameters
- —
- Released
- Mar 2026
- Open weights
- Yes
- Frontier model
- No
Benchmarks
- LiveBench
- 32.0
Compare Nemotron 3 Super 120B A12B with…
Nemotron 3 Super 120B A12B vs DeepSeek V3.1 Terminus$1.00/1MNemotron 3 Super 120B A12B vs Qwen2.5 Coder 32B Instruct$1.00/1MNemotron 3 Super 120B A12B vs MiniMax M2$1.02/1MNemotron 3 Super 120B A12B vs MiniMax M2.5$0.95/1MNemotron 3 Super 120B A12B vs DeepSeek V3.1$0.95/1MNemotron 3 Super 120B A12B vs GLM 4.6V$0.90/1M
FAQ
How much does Nemotron 3 Super 120B A12B cost?
Nemotron 3 Super 120B A12B is priced at $0.30 per 1M input tokens and $1.00 per 1M output tokens. Output tokens cost more than input.
What is Nemotron 3 Super 120B A12B's context window?
Nemotron 3 Super 120B A12B supports a context window of 262K tokens — the maximum prompt plus response length it can handle in a single request.
Is Nemotron 3 Super 120B A12B open weight?
Yes — Nemotron 3 Super 120B A12B has openly available weights.
Data as of 2026-10-16. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.