Models/Nemotron-3-Nano-Omni

Nemotron-3-Nano-OmniActive · Cloud

Nebius AI Studio · Released · NVIDIA Open Model License

Nebius chat model.

Context

262K

Max output

262K

Input

$0.06

Output

$0.24

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

ProviderNebius AI Studio

Released

LicenseNVIDIA Open Model License

InputText

OutputText

Throughput-

Availability-

Related models

GLM-5.3-FlashNebius AI Studio1.0M$0.15 GLM-5.3Nebius AI Studio1.0M$1.40 DeepSeek-V4-Pro-0813Nebius AI Studio0$1.32