token.app › Compare › Nemotron 3 Ultra (batch) vs Inkling Small

Nemotron 3 Ultra (batch) vs Inkling Small

Inkling Small is 1.1× cheaper per token on a blended 3:1 basis. Inkling Small accepts the larger context window (524K).

Head to head
Blended price uses a 3:1 input:output mix
Nemotron 3 Ultra (batch)Inkling Small
ProviderNVIDIAThinkingmachines
Input $/1M$0.300$0.450
Output $/1M$1.80$1.20
Blended $/1M$0.675$0.637
Context window512K524K
Max output—262K
ReleasedJun 2026Jul 2026
LicenceOpen weightsOpen weights
Choose Nemotron 3 Ultra (batch) if…
  • No clear advantage on the data we hold.
Choose Inkling Small if…
  • Costs less per token — $0.637 vs $0.675 blended
  • Larger context window (524K)
  • Newer model (released Jul 2026)
FAQ
Which is better, Nemotron 3 Ultra (batch) or Inkling Small?
We do not hold independently-run benchmark scores covering both Nemotron 3 Ultra (batch) and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Nemotron 3 Ultra (batch) cheaper than Inkling Small?
Inkling Small is cheaper: $0.637 versus $0.675 per million tokens blended at 3:1 input:output. Input alone: $0.300 vs $0.450. Output alone: $1.80 vs $1.20.
What context windows do Nemotron 3 Ultra (batch) and Inkling Small have?
Nemotron 3 Ultra (batch): 512,288 tokens. Inkling Small: 524,288 tokens.
Who makes Nemotron 3 Ultra (batch) and Inkling Small?
Nemotron 3 Ultra (batch) is made by NVIDIA. Inkling Small is made by Thinkingmachines.
Related comparisons
Nemotron 3 Ultra (batch) full details Inkling Small full details Nemotron 3 Ultra (batch) vs Ling 3.0 Tiny (free) Nemotron 3 Ultra (batch) vs Muse Spark 1.2 Nemotron 3 Ultra (batch) vs Qwen3.8 Max Nemotron 3 Ultra (batch) vs DeepSeek V4 Flash Latest Nemotron 3 Ultra (batch) vs DeepSeek V4 Flash 0731 Nemotron 3 Ultra (batch) vs Qwen3.7 Flash