Nemotron 3.5 Super VL 120B A12B
by InferAll · family nemotron · listed Oct 2026RTVW
NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
nvidia/nemotron-3.5-super-vl-120b-a12b- Context window
- 1.0M tokens
- Max output
- 8K tokens
- Input modalities
- text, image, video
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-10-15
- Last updated
- 2026-10-15
← All InferAll listings