Nemotron Nano 3 30B A3B
Nemotron Nano 3 30B A3B is NVIDIA's language model with a 262K context window and up to 228K output tokens, available from 2 providers, starting at $0.050 / 1M input and $0.200 / 1M output. A 30B-parameter hybrid MoE Nemotron Nano 3 model with 3B active parameters, combining Mamba-Transformer architecture for efficient reasoning and agentic tasks.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.050 | $0.200 | |
| $0.050 | $0.240 | |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Nemotron Super 3 120B A12B | 1.0M | $0.090 | $0.450 | Available | |
| Nemotron Nano 3 30B A3B | 262K | $0.050 | $0.200 | Current | |
| Nemotron 3 Ultra | — | — | — | — | Available |
| Nemotron Nano 2 12B | 131K | $0.200 | $0.200 | Available | |
| Nemotron Nano 2 9B | 131K | $0.040 | $0.160 | Deprecating |