Skip to content
LLMs
NVIDIA logo

NVIDIA: Nemotron 3 Nano Omni (free)

by NVIDIA

NVIDIA: Nemotron 3 Nano Omni (free) is a large language model from NVIDIA. It costs Free per million input tokens and Free per million output tokens. Its context window is 256K tokens.

Free tier availableReasoningTool callingOpen weightsaudio inputimage inputvideo input
Input / 1M tokens
Free
Output / 1M tokens
Free
Cached input / 1M
-

Not supported

Context window
256K

tokens

Benchmarks

Independent scores published alongside the catalogue.

Coding index
13.8

About Nemotron 3 Nano Omni (free)

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

Specifications

NVIDIA: Nemotron 3 Nano Omni (free) specifications
Model IDnvidia/nemotron-3-nano-omni-30b-a3b-reasoning
ProviderNVIDIA
Context window256K tokens
Max output66K tokens
Input modalitiestext, audio, image, video
Output modalitiestext
Knowledge cutoff-
Open weightsYes - nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
ReleasedApril 28, 2026

Cheaper alternatives

Models that cost less than Nemotron 3 Nano Omni (free) while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does NVIDIA: Nemotron 3 Nano Omni (free) cost?

Free per million input tokens and Free per million output tokens.

What is the context window of NVIDIA: Nemotron 3 Nano Omni (free)?

256K tokens, with up to 66K tokens of output per request.

Confirm against the source: NVIDIA official pricing.