Models/nvidia.nemotron-nano-12b-v2

nvidia.nemotron-nano-12b-v2Active · Cloud

AWS - Bedrock · Released · NVIDIA Open Model License

Bedrock chat model.

Context

128K

Max output

8K

Input

$0.24

Output

$0.72

Cached in

-

Latency

-

Capabilities

Core

Streaming

Function calling

JSON mode

Structured outputs

Multimodal

Vision

Image input

Audio

Image generation

Video

Advanced

Reasoning

Tool calling

MCP

Prompt caching

Batch API

Embeddings

Details

ProviderAWS - Bedrock

Released

LicenseNVIDIA Open Model License

InputText

OutputText

Throughput-

Availability-

Related models

global.openai.gpt-6-astraAWS - Bedrock1.1M$10.00 openai.gpt-6-astraAWS - Bedrock1.1M$11.00 us.openai.gpt-6-astraAWS - Bedrock1.1M$11.00