Context Window
256,000
Input tokens
Full-context input ≈ $0.00
Model Cost Profile
Developer: nvidia· Tokenizer: Other · Quantization: bf16
Canonical ID: nvidia/nemotron-3-nano-30b-a3b
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.0000
Output: $0.0000
Last synced Apr 24, 2026 · MMLU score via public benchmark data
The NVIDIA Nemotron 3 Nano 30B A3B model offers a substantial context window of 256,000 tokens, making it ideal for applications requiring extensive text comprehension and generation, such as document summarization and conversational AI. Given its free access, teams can leverage this model without incurring input or output costs, significantly lowering the barrier for experimentation and deployment in various projects. This model is particularly suitable for startups and research teams looking to integrate advanced AI capabilities without budget constraints, facilitating innovation in natural language processing tasks.
Context Window
256,000
Input tokens
Full-context input ≈ $0.00
Max Output
—
Not specified
Input Price / 1M
$0.0000
Prompt tokens
Output Price / 1M
$0.0000
Completion tokens
Top Benchmark
79.4
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for NVIDIA: Nemotron 3 Nano 30B A3B (free). The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.000000
Current Output / 1M
$0.000000
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.0000 |
| Output (Completion) | $0.0000 |
Estimate monthly spend for NVIDIA: Nemotron 3 Nano 30B A3B (free) based on your workload.
Estimated Monthly Cost
$0.00
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.