Skip to content
SOLVENCY

Head to head

DeepSeek V4 Pro vs GPT-5.4

DeepSeek V4 Pro: currentGPT-5.4: currentheavy tier

No verdict

Cost per solved task needs a published pass rate for both models. At least one has none, so it is reported as missing rather than estimated.

verified 2026-08-21 · prices from each provider's pricing page

Input $/M tokens

lower is better

  • DeepSeek V4 Pro$1.32
  • GPT-5.4$2.5

Output $/M tokens

lower is better

  • DeepSeek V4 Pro$3.96
  • GPT-5.4$15

Cost per solved task

needs a pass rate for both

  • DeepSeek V4 Promissing
  • GPT-5.4$4.19
DeepSeek V4 ProGPT-5.4
Input $/Mtok$1.32$2.5
Output $/Mtok$3.96$15
Cached input $/Mtok$0.044$0.25
Pass ratemissing59%
Pass rate sourcemissingSEAL
Cost basismissingmodelled
Cost per solved taskmissing$4.19

verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· DeepSeek V4 Pro· GPT-5.4