token.app › Compare › Nemotron 3 Super vs Inkling Small

Nemotron 3 Super vs Inkling Small

Nemotron 3 Super is 3.9× cheaper per token on a blended 3:1 basis. Nemotron 3 Super accepts the larger context window (1M).

Head to head
Blended price uses a 3:1 input:output mix
Nemotron 3 SuperInkling Small
ProviderNVIDIAThinkingmachines
Input $/1M$0.085$0.450
Output $/1M$0.400$1.20
Blended $/1M$0.164$0.637
Context window1M524K
Max output16K262K
ReleasedMar 2026Jul 2026
LicenceOpen weightsOpen weights
Choose Nemotron 3 Super if…
  • Costs less per token — $0.164 vs $0.637 blended
  • Larger context window (1M)
Choose Inkling Small if…
  • Newer model (released Jul 2026)
FAQ
Which is better, Nemotron 3 Super or Inkling Small?
We do not hold independently-run benchmark scores covering both Nemotron 3 Super and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Nemotron 3 Super cheaper than Inkling Small?
Nemotron 3 Super is cheaper: $0.164 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.085 vs $0.450. Output alone: $0.400 vs $1.20.
What context windows do Nemotron 3 Super and Inkling Small have?
Nemotron 3 Super: 1,000,000 tokens. Inkling Small: 524,288 tokens.
Who makes Nemotron 3 Super and Inkling Small?
Nemotron 3 Super is made by NVIDIA. Inkling Small is made by Thinkingmachines.
Related comparisons