NVIDIANemotron 3 Nano Omni 30B A3B Reasoning
- Released
- Apr 29, 2026
- Tracked since
- 2026-07-23
Intelligence index10.3Ranks 368 of 664 models with this metric
Coding index13.8Ranks 223 of 259 models with this metric
Agentic index—Not tested
Capability profile
5 axes vs. site averageNemotron 3 Nano Omni 30B A3B Reasoning
Site average
Some dimensions have no data yet — marked on the chart
Pricing
per 1M tokens- Input
- $0.200
- Output
- $1.09
- Cache read
- $0.200
Performance
- Output throughput
- 267 tokens/sec
- Time to first token
- 470ms
- First answer token
- 7.96s
- End-to-end response
- 9.83s
History
6Intelligence index
14.9→10.3
Output
$0.300→$1.09
Output throughput
315→267
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.5 4B (Reasoning)
AlibabaIntelligence 13.1$0.150−86% - Qwen3.5 4B (Non-reasoning)AlibabaIntelligence 10.8$0.150−86%
- DeepSeek V4 Flash 0420 (Non-reasoning)
DeepSeekIntelligence 18.9$0.200−82% - Qwen3.5 9B (Reasoning)AlibabaIntelligence 13.7$0.200−82%
- Hy3-preview (Reasoning)
TencentIntelligence 22.7$0.210−81%