token.app › Compare › Llama 3.1 8B Instruct vs Inkling Small

Llama 3.1 8B Instruct vs Inkling Small

Inkling Small leads on 2 of 2 shared benchmarks. Llama 3.1 8B Instruct is 11× 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
Llama 3.1 8B InstructInkling Small
ProviderMetaThinkingmachines
Input $/1M$0.050$0.450
Output $/1M$0.080$1.20
Blended $/1M$0.058$0.637
Context window131K524K
Max output118K262K
ReleasedJul 2024Jul 2026
LicenceOpen weightsOpen weights
GPQA Diamond 27.0% 88.5%
OTIS Mock AIME 1.7% 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 3.1 8B Instruct if…
  • Costs less per token — $0.058 vs $0.637 blended
Choose Inkling Small if…
  • Higher GPQA Diamond (88.5% vs 27.0%)
  • Higher OTIS Mock AIME (90.0% vs 1.7%)
  • Larger context window (524K)
  • Newer model (released Jul 2026)
FAQ
Which is better, Llama 3.1 8B Instruct or Inkling Small?
Across the 2 benchmarks both models have independently-run scores for, Llama 3.1 8B Instruct leads on 0 and Inkling Small leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Llama 3.1 8B Instruct cheaper than Inkling Small?
Llama 3.1 8B Instruct is cheaper: $0.058 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.050 vs $0.450. Output alone: $0.080 vs $1.20.
What context windows do Llama 3.1 8B Instruct and Inkling Small have?
Llama 3.1 8B Instruct: 131,072 tokens. Inkling Small: 524,288 tokens.
Who makes Llama 3.1 8B Instruct and Inkling Small?
Llama 3.1 8B Instruct is made by Meta. Inkling Small is made by Thinkingmachines.
Related comparisons
Llama 3.1 8B Instruct full details Inkling Small full details Llama 3.1 8B Instruct vs Flint (free) Llama 3.1 8B Instruct vs MiniMax M3.1 Flash (free) Llama 3.1 8B Instruct vs DeepSeek V4.1 Flash 1017 Llama 3.1 8B Instruct vs Glimpse Llama 3.1 8B Instruct vs Xing4.0 29B A4B (free) Llama 3.1 8B Instruct vs Beam 1.0 501B A23B