GPT-4.1 Mini vs Nemotron 3 Super 120B A12B
Cost and capability comparison. For a sample workload of 1,000 input and 500 output tokens across 100,000 requests/month, Nemotron 3 Super 120B A12B is cheaper by about $76.25/month.
| GPT-4.1 Mini | Nemotron 3 Super 120B A12B | |
|---|---|---|
| Intelligence | ||
| Arena · Overall(LMArena Elo — higher is better) | 1345✓ | — |
| Arena rank (overall) | #107✓ | — |
| Arena · Coding | 1348✓ | — |
| Arena · Math & reasoning | 1335✓ | — |
| Arena · Agentic / tool use | 1338✓ | — |
| Score evidence | Measured | — |
| Pricing (USD / 1M tokens) | ||
| Input | $0.4000 | $0.2100✓ |
| Output | $1.60 | $0.4550✓ |
| Cached input (read) | $0.1000✓ | — |
| Cache write | — | — |
| Blended(3:1 input:output blend) | $0.7000 | $0.2712✓ |
| Specs & capabilities | ||
| Provider | OpenAI | Nvidia |
| Context window | 1M (1,000,000)✓ | 262K (262,144) |
| Max output | 32,768 | 262,144✓ |
| Modalities | text, image | text |
| Vision | Yes | No |
| Tool use | Yes | Yes |
| Reasoning | No | Yes |
| Prompt caching | Yes | No |
| Batch pricing | Yes | No |
| Tokenizer | o200k_base | approx |
| Release date | — | — |
| Status | ga | ga |
Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 18 September 2026. Scores are a relative signal, not an absolute measure of capability. A Measured score was voted on directly; an Estimated score is inherited from an identical base model (a regional/creator-prefixed hosting duplicate). See our methodology.
Compare on your own workload
GPT-4.1 Mini and Nemotron 3 Super 120B A12B are pre-loaded. Adjust the tokens and monthly volume to see which is cheaper for your usage.
Used unless you set active users below.
Results update automatically as you type.
| Nemotron 3 Super 120B A12B | Nvidia | $0.000438 | $43.75 | $525.00 | 262,144 |
| GPT-4.1 Mini | OpenAI | $0.00120 | $120.00 | $1,440.00 | 1,000,000 |
FAQ
Which is cheaper, GPT-4.1 Mini or Nemotron 3 Super 120B A12B?
For a workload of 1,000 input and 500 output tokens over 100,000 requests/month, Nemotron 3 Super 120B A12B is cheaper, costing about $43.75/month versus $120.00/month.
What is the context window of GPT-4.1 Mini and Nemotron 3 Super 120B A12B?
GPT-4.1 Mini supports 1,000,000 tokens, while Nemotron 3 Super 120B A12B supports 262,144 tokens.
Estimates for planning only. Verify current pricing with each provider.