Skip to main content
NVIDIAJan 27, 2026

NVIDIA Nemotron 3 Nano 30B

nvidia-nemotron-3-nano-30b-a3bPrivateOpen weights

NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.

$0.075/$0.30
per 1M in / out
128K
context window
16K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 9%49.8%
Blended pricecheaper than 99%$0.13
Context windowlarger than 2%128K
Max outputlarger than 8%16K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InText
OutText
Streamingstream: true
Function callingtoolsStructured outputsresponse_format
Web searchenable_web_search

Not supportedreasoning, image input, video input, audio input, X search, prompt caching and log probabilities

Benchmarks

GPQA Diamond
49.8%127th of 139 · OpenAI GPT OSS 120B scores higher for less

Specs

Model ID
nvidia-nemotron-3-nano-30b-a3b
Endpoint
POST /api/v1/chat/completions
Context window
128,000 tokens
Max output
16,384 tokens
Reasoning
None
Precision
FP8
Privacy
Private
Added
Jan 27, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
NVIDIA Nemotron 3 Nano 30B$0.075$0.3049.8%128K16K——
Mistral Small 3.2 24B Instruct$0.0938$0.2541.4%256K16K——
OpenAI GPT OSS 120B$0.07$0.3066.7%128K16K——
GLM 4.7 Flash Heretic$0.07$0.4035.4%200K24K——
Google Gemma 3 27B Instruct$0.12$0.2048.0%198K16K——

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$0.075per 1M tokens
Output$0.30per 1M tokens

Estimate a workload

$0.0003per request
$3.00for 10,000 requests

Blended price against similar models

NVIDIA Nemotron 3 Nano 30B$0.1312

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia-nemotron-3-nano-30b-a3b",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelnvidia-nemotron-3-nano-30b-a3bRequired
messagestextContent parts the model reads
max_completion_tokensUp to 16,384
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations