Skip to content
SOLVENCY

Head to head

Claude Haiku 4.5 vs DeepSeek V4 Pro

Claude Haiku 4.5: currentDeepSeek V4 Pro: 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

  • Claude Haiku 4.5$1
  • DeepSeek V4 Pro$1.32

Output $/M tokens

lower is better

  • Claude Haiku 4.5$5
  • DeepSeek V4 Pro$3.96

Cost per solved task

needs a pass rate for both

  • Claude Haiku 4.5missing
  • DeepSeek V4 Promissing
Claude Haiku 4.5DeepSeek V4 Pro
Input $/Mtok$1$1.32
Output $/Mtok$5$3.96
Cached input $/Mtok$0.1$0.044
Pass ratemissingmissing
Pass rate sourcemissingmissing
Cost basismissingmissing
Cost per solved taskmissingmissing

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