token.app โ€บ Compare โ€บ DeepSeek V4 Flash 0731 vs Inkling

DeepSeek V4 Flash 0731 vs Inkling

DeepSeek V4 Flash 0731 leads on 4 of 4 shared benchmarks. DeepSeek V4 Flash 0731 is 2.7ร— cheaper per token on a blended 3:1 basis. DeepSeek V4 Flash 0731 accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
DeepSeek V4 Flash 0731Inkling
ProviderDeepSeekThinkingmachines
Input $/1M$0.440$1.00
Output $/1M$1.32$4.05
Blended $/1M$0.660$1.76
Context window1.0M524K
Max output131K472K
ReleasedJul 2026Jul 2026
LicenceOpen weightsOpen weights
GPQA Diamond 91.0% 88.3%
FrontierMath T1โ€“3 57.5% 33.3%
FrontierMath T4 24.4% 4.9%
OTIS Mock AIME 94.4% 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 DeepSeek V4 Flash 0731 ifโ€ฆ
  • Costs less per token โ€” $0.660 vs $1.76 blended
  • Higher GPQA Diamond (91.0% vs 88.3%)
  • Higher FrontierMath T1โ€“3 (57.5% vs 33.3%)
  • Higher FrontierMath T4 (24.4% vs 4.9%)
  • Higher OTIS Mock AIME (94.4% vs 88.9%)
  • Larger context window (1.0M)
  • Newer model (released Jul 2026)
Choose Inkling ifโ€ฆ
  • No clear advantage on the data we hold.
FAQ
Which is better, DeepSeek V4 Flash 0731 or Inkling?
Across the 4 benchmarks both models have independently-run scores for, DeepSeek V4 Flash 0731 leads on 4 and Inkling leads on 0. Benchmarks are one input โ€” price and context window are on this page too.
Is DeepSeek V4 Flash 0731 cheaper than Inkling?
DeepSeek V4 Flash 0731 is cheaper: $0.660 versus $1.76 per million tokens blended at 3:1 input:output. Input alone: $0.440 vs $1.00. Output alone: $1.32 vs $4.05.
What context windows do DeepSeek V4 Flash 0731 and Inkling have?
DeepSeek V4 Flash 0731: 1,048,576 tokens. Inkling: 524,288 tokens.
Who makes DeepSeek V4 Flash 0731 and Inkling?
DeepSeek V4 Flash 0731 is made by DeepSeek. Inkling is made by Thinkingmachines.
Related comparisons