token.app › Compare › Qwen2.5 72B Instruct vs Inkling

Qwen2.5 72B Instruct vs Inkling

Inkling leads on 2 of 2 shared benchmarks. Qwen2.5 72B Instruct is 4.8× cheaper per token on a blended 3:1 basis. Inkling accepts the larger context window (524K).

Head to head
Blended price uses a 3:1 input:output mix
Qwen2.5 72B InstructInkling
ProviderAlibabaThinkingmachines
Input $/1M$0.360$1.00
Output $/1M$0.400$4.05
Blended $/1M$0.370$1.76
Context window33K524K
Max output16K472K
ReleasedSep 2024Jul 2026
LicenceOpen weightsOpen weights
GPQA Diamond 49.1% 88.3%
OTIS Mock AIME 8.1% 88.9%
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 Qwen2.5 72B Instruct if…
  • Costs less per token — $0.370 vs $1.76 blended
Choose Inkling if…
  • Higher GPQA Diamond (88.3% vs 49.1%)
  • Higher OTIS Mock AIME (88.9% vs 8.1%)
  • Larger context window (524K)
  • Newer model (released Jul 2026)
FAQ
Which is better, Qwen2.5 72B Instruct or Inkling?
Across the 2 benchmarks both models have independently-run scores for, Qwen2.5 72B Instruct leads on 0 and Inkling leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Qwen2.5 72B Instruct cheaper than Inkling?
Qwen2.5 72B Instruct is cheaper: $0.370 versus $1.76 per million tokens blended at 3:1 input:output. Input alone: $0.360 vs $1.00. Output alone: $0.400 vs $4.05.
What context windows do Qwen2.5 72B Instruct and Inkling have?
Qwen2.5 72B Instruct: 32,768 tokens. Inkling: 524,288 tokens.
Who makes Qwen2.5 72B Instruct and Inkling?
Qwen2.5 72B Instruct is made by Alibaba. Inkling is made by Thinkingmachines.
Related comparisons
Qwen2.5 72B Instruct full details Inkling full details Qwen2.5 72B Instruct vs Flint (free) Qwen2.5 72B Instruct vs MiniMax M3.1 Flash (free) Qwen2.5 72B Instruct vs DeepSeek V4.1 Flash 1017 Qwen2.5 72B Instruct vs Glimpse Qwen2.5 72B Instruct vs Xing4.0 29B A4B (free) Qwen2.5 72B Instruct vs Beam 1.0 501B A23B