Skip to content
SOLVENCY

Head to head

DeepSeek V4 Pro vs Claude Opus 4.5

DeepSeek V4 Pro: currentClaude Opus 4.5: legacyheavy 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
  • Claude Opus 4.5$5

Output $/M tokens

lower is better

  • DeepSeek V4 Pro$3.96
  • Claude Opus 4.5$25

Cost per solved task

needs a pass rate for both

  • DeepSeek V4 Promissing
  • Claude Opus 4.5$9.81
DeepSeek V4 ProClaude Opus 4.5
Input $/Mtok$1.32$5
Output $/Mtok$3.96$25
Cached input $/Mtok$0.044$0.5
Pass ratemissing46%
Pass rate sourcemissingSEAL
Cost basismissingmodelled
Cost per solved taskmissing$9.81

verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· DeepSeek V4 Pro· Claude Opus 4.5