token.app › Compare › Llama 4 Scout vs Inkling Small

Llama 4 Scout vs Inkling Small

Inkling Small leads on 2 of 2 shared benchmarks. Llama 4 Scout is 4.2× cheaper per token on a blended 3:1 basis. Llama 4 Scout accepts the larger context window (1.3M).

Head to head
Blended price uses a 3:1 input:output mix
Llama 4 ScoutInkling Small
ProviderMetaThinkingmachines
Input $/1M$0.100$0.450
Output $/1M$0.300$1.20
Blended $/1M$0.150$0.637
Context window1.3M524K
Max output16K262K
ReleasedApr 2025Jul 2026
LicenceOpen weightsOpen weights
GPQA Diamond 51.8% 88.5%
OTIS Mock AIME 7.8% 90.0%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Llama 4 Scout if…
  • Costs less per token — $0.150 vs $0.637 blended
  • Larger context window (1.3M)
Choose Inkling Small if…
  • Higher GPQA Diamond (88.5% vs 51.8%)
  • Higher OTIS Mock AIME (90.0% vs 7.8%)
  • Newer model (released Jul 2026)
FAQ
Which is better, Llama 4 Scout or Inkling Small?
Across the 2 benchmarks both models have independently-run scores for, Llama 4 Scout leads on 0 and Inkling Small leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Llama 4 Scout cheaper than Inkling Small?
Llama 4 Scout is cheaper: $0.150 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.450. Output alone: $0.300 vs $1.20.
What context windows do Llama 4 Scout and Inkling Small have?
Llama 4 Scout: 1,310,720 tokens. Inkling Small: 524,288 tokens.
Who makes Llama 4 Scout and Inkling Small?
Llama 4 Scout is made by Meta. Inkling Small is made by Thinkingmachines.
Related comparisons