token.app โ€บ Compare โ€บ DeepSeek V4 Pro 0423 vs Inkling Small

DeepSeek V4 Pro 0423 vs Inkling Small

DeepSeek V4 Pro 0423 and Inkling Small split the 4 shared benchmarks evenly. Inkling Small is 1.9ร— cheaper per token on a blended 3:1 basis. DeepSeek V4 Pro 0423 accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
DeepSeek V4 Pro 0423Inkling Small
ProviderDeepSeekThinkingmachines
Input $/1M$0.955$0.450
Output $/1M$1.91$1.20
Blended $/1M$1.19$0.637
Context window1.0M524K
Max output384K262K
ReleasedApr 2026Jul 2026
LicenceOpen weightsOpen weights
GPQA Diamond 90.9% 88.5%
FrontierMath T1โ€“3 45.3% 46.3%
FrontierMath T4 2.4% 17.1%
OTIS Mock AIME 96.7% 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 DeepSeek V4 Pro 0423 ifโ€ฆ
  • Higher GPQA Diamond (90.9% vs 88.5%)
  • Higher OTIS Mock AIME (96.7% vs 90.0%)
  • Larger context window (1.0M)
Choose Inkling Small ifโ€ฆ
  • Costs less per token โ€” $0.637 vs $1.19 blended
  • Higher FrontierMath T1โ€“3 (46.3% vs 45.3%)
  • Higher FrontierMath T4 (17.1% vs 2.4%)
  • Newer model (released Jul 2026)
FAQ
Which is better, DeepSeek V4 Pro 0423 or Inkling Small?
Across the 4 benchmarks both models have independently-run scores for, DeepSeek V4 Pro 0423 leads on 2 and Inkling Small leads on 2. Benchmarks are one input โ€” price and context window are on this page too.
Is DeepSeek V4 Pro 0423 cheaper than Inkling Small?
Inkling Small is cheaper: $0.637 versus $1.19 per million tokens blended at 3:1 input:output. Input alone: $0.955 vs $0.450. Output alone: $1.91 vs $1.20.
What context windows do DeepSeek V4 Pro 0423 and Inkling Small have?
DeepSeek V4 Pro 0423: 1,048,576 tokens. Inkling Small: 524,288 tokens.
Who makes DeepSeek V4 Pro 0423 and Inkling Small?
DeepSeek V4 Pro 0423 is made by DeepSeek. Inkling Small is made by Thinkingmachines.
Related comparisons