---
id: "nvidia/nemotron-3-nano-30b-a3b"
also: ["nvidia/nemotron-3-nano-30b-a3b", "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "requesty/nvidia/nemotron-3-nano-30b-a3b", "vercel/nvidia/nemotron-3-nano-30b-a3b"]
cheapest_list_usd_per_m: "0.05 in, 0.2 out, at crusoe/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.0298 in, 0.2394 out, at nebius/fp8 on openrouter"
context: 262144
max_output: 235929
input: ["text"]
output: ["text"]
released: "2025-12-14"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 8
gateways: "openrouter (4), requesty (2), vercel (2)"
no_training: 7
trains: 1
retains_prompts: 2
coding: 14.4000
agentic: 1
---
# NVIDIA: Nemotron 3 Nano 30B A3B

NVIDIA Nemotron 3 Nano is an open small reasoning model optimized for fast, cost-efficient inference in agentic and production workloads. Built with a hybrid Mixture-of-Experts (MoE) and Mamba-Transformer architecture, it delivers strong multi-step reasoning, high token throughput, stable latency with predictable cost, and efficient deployment for agent-based systems. Designed for real-world AI systems where reasoning can generate significantly more tokens per prompt, Nemotron Nano reduces compu