token.app › Compare › DeepSeek V4 Flash 0423 vs Inkling Small

DeepSeek V4 Flash 0423 vs Inkling Small

DeepSeek V4 Flash 0423 is 3.6× cheaper per token on a blended 3:1 basis. DeepSeek V4 Flash 0423 accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
DeepSeek V4 Flash 0423Inkling Small
ProviderDeepSeekThinkingmachines
Input $/1M$0.140$0.450
Output $/1M$0.280$1.20
Blended $/1M$0.175$0.637
Context window1.0M524K
Max output393K262K
ReleasedApr 2026Jul 2026
LicenceOpen weightsOpen weights
Choose DeepSeek V4 Flash 0423 if…
  • Costs less per token — $0.175 vs $0.637 blended
  • Larger context window (1.0M)
Choose Inkling Small if…
  • Newer model (released Jul 2026)
FAQ
Which is better, DeepSeek V4 Flash 0423 or Inkling Small?
We do not hold independently-run benchmark scores covering both DeepSeek V4 Flash 0423 and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is DeepSeek V4 Flash 0423 cheaper than Inkling Small?
DeepSeek V4 Flash 0423 is cheaper: $0.175 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.140 vs $0.450. Output alone: $0.280 vs $1.20.
What context windows do DeepSeek V4 Flash 0423 and Inkling Small have?
DeepSeek V4 Flash 0423: 1,048,576 tokens. Inkling Small: 524,288 tokens.
Who makes DeepSeek V4 Flash 0423 and Inkling Small?
DeepSeek V4 Flash 0423 is made by DeepSeek. Inkling Small is made by Thinkingmachines.
Related comparisons
DeepSeek V4 Flash 0423 full details Inkling Small full details DeepSeek V4 Flash 0423 vs Ling 3.0 Tiny (free) DeepSeek V4 Flash 0423 vs Muse Spark 1.2 DeepSeek V4 Flash 0423 vs Qwen3.8 Max DeepSeek V4 Flash 0423 vs DeepSeek V4 Flash Latest DeepSeek V4 Flash 0423 vs DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0423 vs Qwen3.7 Flash