NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIAOpen weights
NVIDIA: Nemotron 3 Nano 30B A3B by NVIDIA costs $0.06 per 1M input tokens and $0.24 per 1M output tokens, with a 262K-token context window.
Pricing
Input (per 1M tokens)
$0.06
Output (per 1M tokens)
$0.24
Cached input (per 1M)
—
Specifications
- Provider
- NVIDIA
- Context window
- 262K tokens
- Parameters
- 32B
- Released
- Dec 2025
- Open weights
- Yes
- Frontier model
- No
- Hugging Face
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Speed & latency
Time to first token
0.26s
Fastest host: deepinfra (via vercel-ai-gateway).
Compare NVIDIA: Nemotron 3 Nano 30B A3B with…
NVIDIA: Nemotron 3 Nano 30B A3B vs Nova Lite 1.0$0.24/1MNVIDIA: Nemotron 3 Nano 30B A3B vs Granite 4.2 8B$0.25/1MNVIDIA: Nemotron 3 Nano 30B A3B vs Gemma 4 26B A4B$0.26/1MNVIDIA: Nemotron 3 Nano 30B A3B vs mistral-7b-instruct-v0.2$0.22/1MNVIDIA: Nemotron 3 Nano 30B A3B vs DeepSeek Reasoner$0.28/1MNVIDIA: Nemotron 3 Nano 30B A3B vs Qwen3 32B$0.28/1M
FAQ
How much does NVIDIA: Nemotron 3 Nano 30B A3B cost?
NVIDIA: Nemotron 3 Nano 30B A3B is priced at $0.06 per 1M input tokens and $0.24 per 1M output tokens. Output tokens cost more than input.
What is NVIDIA: Nemotron 3 Nano 30B A3B's context window?
NVIDIA: Nemotron 3 Nano 30B A3B supports a context window of 262K tokens — the maximum prompt plus response length it can handle in a single request.
Is NVIDIA: Nemotron 3 Nano 30B A3B open weight?
Yes — NVIDIA: Nemotron 3 Nano 30B A3B has openly available weights.
Data as of 2026-10-16. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.