The Orchestrator › Models › NVIDIA
NVIDIA: Nvidia Nemotron Nano 12B V2 VL
The model is an auto-regressive vision language model that uses an optimized transformer architecture. The model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&A and summarization capabilities.
Specifications
| Provider | NVIDIA |
| Model ID | nvidia/nemotron-nano-12b-v2-vl |
| Context window | 131K tokens (131,072) |
| Modalities | text + image → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2025-10-28 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | nvidia/nemotron-nano-12b-v2-vl | $0.2 | $0.6 | 131K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.2 | $0.6 | 131K |
Capabilities
Vision (image input)Agentic tool useControllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning