Nemotron 3.5 Super VL 120B A12B
Nemotron 3.5 Super VL 120B A12B is a model by NVIDIA for reasoning, it stands 218th of 273 on ARC-AGI-1, and 3 sellers in the catalogue publish a price for it.
text + image + video → text · made by NVIDIA
Sold by 3 ways
| Seller | Lane | Rate |
|---|---|---|
| Together AI aggregator | standard | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedmodels.dev · read 2026-10-31 |
| Baseten aggregator | standard | $0.2per Mtok in$0.5per Mtok out$0.04per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| Nebius Token Factory 0 ways | $0.3per Mtok in$0.9per Mtok out$0.3per Mtok cached | |
| Nebius Token Factory aggregatornot on the seller's list today | standard | $0.3per Mtok in$0.9per Mtok out$0.3per Mtok cachedmodels.dev · read 2026-10-16 |
Measured 4 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 218thof 273 | ARC-AGI-1 (Public Eval) | Score (%) (high) | 39.75 |
| 219thof 282 | ARC-AGI-2 (Public Eval) | Score (%) (high) | 1.94 |
| 240thof 298 | ARC-AGI-2 (Semi-Private) | Score (%) (medium) | 1.94 |
| 248thof 298 | ARC-AGI-1 (Semi-Private) | Score (%) (high) | 22.67 |
About
Nemotron 3.5 Super VL 120B A12B — a text model from NVIDIA, sold by 2 companies from $0.15 in and $0.5 out per million tokens, placed 219th of 282 on ARC-AGI-2 (Public Eval).
It takes text, images and video and returns text, with a context window of 1,048,576 tokens. It was published in October 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning. Two companies sell it. The cheapest is $0.15 in and $0.5 out per million tokens at Together AI. It has been measured on 4 boards, and stands best at 219th of 282 on ARC-AGI-2 (Public Eval).
Every current figure
- Maker
- NVIDIA
- Register
- model
- Takes
- text + image + video
- Returns
- text
- Context
- 1,048,576 tokens
- Published
- October 2026
- Parameters
- 120 billion · read from its own name, the total of a mixture
- Sellers
- 2
- Maker's own price
- not read
- Price
- $0.15 in and $0.5 out per million tokens — Together AI
- Boards
- 4
- Best place
- 219th of 282 — ARC-AGI-2 (Public Eval)