# Nemotron 3.5 Super VL 120B A12B API prices

Nemotron 3.5 Super VL 120B A12B (nemotron-super) — 1.0M context, 1.0M max output.
7 metered per-token offers from 9 providers, in USD per 1M tokens.
Prices as of 2026-11-22.

| Provider | API model ID | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- | --- |
| Pioneer | `nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4` | $0.08 | $0.45 | $0.04 | 262k |
| Together AI | `nvidia/NVIDIA-Nemotron-3.5-Super-VL` | $0.15 | $0.5 | $0.02 | 262k |
| CommandCode | `nvidia/nemotron-3.5-super-vl` | $0.2 | $0.5 | $0.04 | 262k |
| Cortecs | `nemotron-3.5-super-vl` | $0.204 | $0.51 | $0.041 | 1.0M |
| Nebius Token Factory | `nvidia/Nemotron-3.5-Super-VL` | $0.3 | $0.9 | $0.06 | 1.0M |
| Thinking Machines | `nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16` | $0.57 | $1.44 | $0.114 | 66k |
| Thinking Machines | `nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:262144` | $0.57 | $1.44 | $0.114 | 262k |

## Summary

- Cheapest input: $0.08 per 1M tokens (Pioneer)
- Cheapest output: $0.45 per 1M tokens (Pioneer)
- First-party: not listed separately
- Free offers: InferAll, Nvidia
- Subscription plans (not per-token): none
- Released: 2026-10-15
- Inputs: image, text, video

## FAQ

### What is the cheapest Nemotron 3.5 Super VL 120B A12B API?

As of Nov 22, 2026, Pioneer has the lowest Nemotron 3.5 Super VL 120B A12B output price at $0.45 per 1M tokens, and Pioneer has the lowest input price at $0.08 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Nemotron 3.5 Super VL 120B A12B?

9 providers list Nemotron 3.5 Super VL 120B A12B on Sovyron; 7 of them sell it at a metered per-token price.

### Is Nemotron 3.5 Super VL 120B A12B free?

2 providers list a free-tier offer: InferAll, Nvidia. Free tiers usually have rate limits.

### What is the context window of Nemotron 3.5 Super VL 120B A12B?

Nemotron 3.5 Super VL 120B A12B supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/nemotron-3-5-super-vl-120b-a12b/
Full dataset: https://sovyron.com/data/catalog.json
