Routerbase
Browse
GitHub
llms.txt
Back to Models
Compare All
Nemotron 3 Nano 30B A3B
nvidia
nvidia/nemotron-3-nano-30b-a3b
$
Very cheap
$0.125
per 1M tokens
Capabilities
Tools
JSON
Quality
39%
Performance
84/100
Context
262K
Speed
197 tok/s
Developer Tier
Standard
Similar Models
Cheaper Alternatives
Explore by Capability
All Tool-calling models
All JSON Mode models
All 128K+ context models
View on OpenRouter
External link
Similar Models
See all →
Qwen2.5 Coder 7B Instruct
qwen
$0.06
38%
Gemma 3n 4B
google
$0.03
43%
Llama 3.3 70B Instruct
meta-llama
$0.21
44%
Cheaper Alternatives
See budget models →
Qwen3 235B A22B Instruct 2507
qwen
$0.09
88%
Gemma 3 27B
google
$0.07
64%
Gemma 3 12B
google
$0.09
52%