token.app › Compare › Nemotron 3 Nano 30B A3B vs Mercury 3

Nemotron 3 Nano 30B A3B vs Mercury 3

Nemotron 3 Nano 30B A3B is 1.5× cheaper per token on a blended 3:1 basis. Mercury 3 accepts the larger context window (1M).

Head to head
Blended price uses a 3:1 input:output mix
Nemotron 3 Nano 30B A3BMercury 3
ProviderNVIDIAInception
Input $/1M$0.060$0.100
Output $/1M$0.240$0.350
Blended $/1M$0.105$0.163
Context window262K1M
Max output236K131K
ReleasedDec 2025Oct 2026
LicenceOpen weightsProprietary
Choose Nemotron 3 Nano 30B A3B if…
  • Costs less per token — $0.105 vs $0.163 blended
  • Open weights — self-hostable
Choose Mercury 3 if…
  • Larger context window (1M)
  • Newer model (released Oct 2026)
FAQ
Which is better, Nemotron 3 Nano 30B A3B or Mercury 3?
We do not hold independently-run benchmark scores covering both Nemotron 3 Nano 30B A3B and Mercury 3, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Nemotron 3 Nano 30B A3B cheaper than Mercury 3?
Nemotron 3 Nano 30B A3B is cheaper: $0.105 versus $0.163 per million tokens blended at 3:1 input:output. Input alone: $0.060 vs $0.100. Output alone: $0.240 vs $0.350.
What context windows do Nemotron 3 Nano 30B A3B and Mercury 3 have?
Nemotron 3 Nano 30B A3B: 262,144 tokens. Mercury 3: 1,000,000 tokens.
Who makes Nemotron 3 Nano 30B A3B and Mercury 3?
Nemotron 3 Nano 30B A3B is made by NVIDIA. Mercury 3 is made by Inception.
Related comparisons
Nemotron 3 Nano 30B A3B full details Mercury 3 full details Nemotron 3 Nano 30B A3B vs Flint (free) Nemotron 3 Nano 30B A3B vs MiniMax M3.1 Flash (free) Nemotron 3 Nano 30B A3B vs DeepSeek V4.1 Flash 1017 Nemotron 3 Nano 30B A3B vs Glimpse Nemotron 3 Nano 30B A3B vs Xing4.0 29B A4B (free) Nemotron 3 Nano 30B A3B vs Beam 1.0 501B A23B