Nemotron Nano 2 12B
Nemotron Nano 2 12B is NVIDIA's language model with a 131K context window and up to 8K output tokens, available from 2 providers, starting at $0.200 / 1M input and $0.200 / 1M output. A 12B-parameter hybrid LLM from NVIDIA's Nemotron Nano v2 series, trained from scratch as a unified model supporting both reasoning and non-reasoning modes.
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
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 | Batch | Flex | Priority | ||||
|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 Amazon Bedrock | $0.200 | $0.600 | $0.100 | $0.300 | $0.100 | $0.300 | $0.350 | $1.05 |
 Fireworks AI | $0.200 | $0.200 | — | — | — | — | — | — |
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 | Available | |
| Nemotron Nano 2 12B | 131K | $0.200 | $0.200 | Current | |
| Nemotron Nano 2 9B | 131K | $0.040 | $0.160 | Available |