The Orchestrator › Models › NVIDIA
NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
Specifications
| Provider | NVIDIA |
| Model ID | nvidia/nemotron-3-nano-30b-a3b |
| Context window | 262K tokens (262,144) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2025-12-14 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | nvidia/nemotron-3-nano-30b-a3b | $0.06 | $0.24 | 262K |
| standard | TrustedRouter | nvidia/nemotron-3-nano-30b-a3b | $0.053 | $0.211 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.053 | $0.211 | 262K |
| 2026-11-14 | $0.06 | $0.24 | 262K |
Capabilities
Agentic tool useStructured outputs256K+ context windowControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p