Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3bSmall Nemotron 3 MoE for efficient coding, math, and long-context agents
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...
Context
128K
128,000 tokens
Max output
16K
16,384 tokens
Input
$0.07
per 1M tokens
Output
$0.30
per 1M tokens
Providers
15
15 listings
Intelligence
8.9
Intelligence Index
Pricing
USD per 1M tokens · listed by Venice AI
| Token type | Standard |
|---|---|
| Input | $0.07 |
| Output | $0.30 |
Lowest input price across providers: $0.05.
Capabilities
ReasoningNo
On / off
Tool callYes
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningYes
Field: reasoning_content
Open weightsYes
ModeratedNo
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
- Intelligence8.9#167 of 208
- Coding14.4#100 of 112
- Agentic1#75 of 86
- ArenaNot scored—
Rankings
Position on each OneAtlas leaderboard
Providers · 15
15 listings
Venice AI
NanoGPT
Vercel AI Gateway
Kilo Gateway
Eden AI
Merge Gateway
Amazon BedrockCortecs
Novita AI
Deep Infra
Kenari
Thinking Machines
Ollama Cloud
Crusoe
Infomaniak| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Amazon Bedrock | nvidia.nemotron-nano-3-30b | 262K | — | 8K | $0.06 | $0.24 | — | — | — | — | — | Yes | Yes | Yes | Yes | Dec 23, 2025 |
| Cortecs | nvidia-nemotron-3-nano-30b-a3b | 256K | — | 256K | $0.06 | $0.24 | — | — | — | — | — | Yes | Yes | Yes | No | Dec 15, 2025 |
| Crusoe | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | 262K | — | 262K | $0.05 | $0.20 | — | $0.03 | — | — | — | Yes | Yes | Unknown | Yes | Dec 15, 2025 |
| Deep Infra | nvidia/Nemotron-3-Nano-30B-A3B | 262K | — | 262K | $0.05 | $0.20 | — | $0.03 | — | — | — | Yes | Yes | Unknown | Yes | Dec 15, 2025 |
| Eden AI | deepinfra/nvidia/Nemotron-3-Nano-30B-A3B | 262K | — | 262K | $0.05 | $0.20 | — | $0.03 | — | — | — | Yes | Yes | Yes | Yes | Dec 15, 2025 |
| Infomaniak | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 | 1M | 1M | 262K | $0.06 | $0.25 | — | — | — | — | — | Yes | Yes | Unknown | Yes | Dec 15, 2025 |
| Kenari | nemotron-3-nano-30b-a3b | 262K | — | 262K | — | — | — | — | — | — | — | Yes | Yes | Unknown | Yes | Dec 15, 2025 |
| Kilo Gateway | nvidia/nemotron-3-nano-30b-a3b | 262K | — | 236K | $0.05 | $0.20 | — | — | — | — | — | Yes | Yes | Yes | Yes | Dec 15, 2025 |
| Merge Gateway | nvidia/nemotron-3-nano-30b-a3b | 256K | — | 32K | $0.05 | $0.20 | — | — | — | — | — | Yes | No | No | Yes | Dec 15, 2025 |
| NanoGPT | nvidia/nemotron-3-nano-30b-a3b | 262K | 262K | 236K | $0.17 | $0.68 | — | $0.09 | — | — | — | No | No | No | Yes | Dec 15, 2025 |
| Novita AI | nvidia/nemotron-3-nano-30b-a3b | 262K | — | 33K | $0.05 | $0.20 | — | — | — | — | — | Yes | Yes | Yes | Yes | Dec 15, 2025 |
| Ollama Cloud | nemotron-3-nano:30b | 1.05M | — | 131K | $0.06 | $0.24 | — | — | — | — | — | Yes | Yes | No | Yes | Dec 15, 2025 |
| Thinking Machines | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 66K | — | 66K | $0.20 | $0.49 | — | $0.04 | — | — | — | Yes | Yes | Unknown | Yes | Dec 15, 2025 |
| Venice AI | nvidia-nemotron-3-nano-30b-a3b | 128K | — | 16K | $0.07 | $0.30 | — | — | — | — | — | No | Yes | Yes | Yes | Dec 15, 2025 |
| Vercel AI Gateway | nvidia/nemotron-3-nano-30b-a3b | 262K | — | 262K | $0.05 | $0.20 | — | $0.03 | — | — | — | Yes | No | Unknown | Yes | Dec 15, 2025 |