Context Window
262,144
Input tokens
Full-context input ≈ $0.01
Model Cost Profile
Developer: nvidia· Tokenizer: Other · Quantization: fp4
Canonical ID: nvidia/nemotron-3-nano-30b-a3b
Pricing updated Apr 23, 2026
Live Pricing
Input: $0.0500
Output: $0.2000
Last synced Apr 23, 2026 · MMLU score via public benchmark data
The NVIDIA Nemotron 3 Nano 30B A3B model features an extensive context window of 262,144 tokens, making it well-suited for applications requiring in-depth analysis and long-form content generation. Teams leveraging this API can benefit from a competitive input cost of $0.05 per 1 million tokens and an output cost of $0.20 per 1 million tokens, allowing for scalable usage in projects like chatbots, document summarization, and complex data processing. This pricing structure enables organizations to optimize their budget while harnessing advanced AI capabilities for diverse business needs.
Context Window
262,144
Input tokens
Full-context input ≈ $0.01
Max Output
—
Not specified
Input Price / 1M
$0.0500
Prompt tokens
Output Price / 1M
$0.2000
Completion tokens
Top Benchmark
79.4
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for NVIDIA: Nemotron 3 Nano 30B A3B. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.0500
Current Output / 1M
$0.2000
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.0500 |
| Output (Completion) | $0.2000 |
Estimate monthly spend for NVIDIA: Nemotron 3 Nano 30B A3B based on your workload.
Estimated Monthly Cost
$3.65
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.