NVIDIA

Nemotron 3 Nano Omni 30B A3B Reasoning

AI model by NVIDIA. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.07
Output$0.30
Blended (3:1)$0.13

Source: Artificial Analysis

Performance

Output Speed319 tok/s
Time to First Token539ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Nemotron 3 Nano Omni 30B A3B Reasoning is a budget-tier option from NVIDIA at $0.30/M output tokens. Despite the low price, it scores competitively on IFBench (63.2%) and GPQA Diamond (46.9%) — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Nemotron 3 Nano Omni 30B A3B Reasoning reports 319 tok/s output speed and 539ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.

Cost model. For a workload of 1M input tokens + 100K output tokens, Nemotron 3 Nano Omni 30B A3B Reasoning costs $0.10 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-03.

Compare with similar models

ModelInputOutputSpeed
Nemotron 3 Nano Omni 30B A3B ReasoningCurrent
$0.07$0.30319 tok/s
Gemma 4 12B (Non-reasoning)
$0.10$0.30129 tok/s
Gemma 4 12B (Reasoning)
$0.10$0.30135 tok/s
Ling 2.6 Flash
$0.10$0.3089 tok/s
Mistral Small 3
$0.10$0.300 tok/s
Mistral Small 3.1
$0.10$0.300 tok/s

Example Costs

Single Request
$0.0002
1.0K in / 500 out
1K Requests/day
$0.2250
1.0M in / 500.0K out
10K Requests/day
$2.25
10.0M in / 5.0M out