Skip to content
SOLVENCY

Head to head

Mistral Medium 3.5 vs GPT-4.1

Mistral Medium 3.5: currentGPT-4.1: 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

  • Mistral Medium 3.5$1.5
  • GPT-4.1$2

Output $/M tokens

lower is better

  • Mistral Medium 3.5$7.5
  • GPT-4.1$8

Cost per solved task

needs a pass rate for both

  • Mistral Medium 3.5missing
  • GPT-4.1$5.15
Mistral Medium 3.5GPT-4.1
Input $/Mtok$1.5$2
Output $/Mtok$7.5$8
Cached input $/Mtokmissing$0.5
Pass ratemissing52%
Pass rate sourcemissingAider
Cost basismissingmodelled
Cost per solved taskmissing$5.15

verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· Mistral Medium 3.5· GPT-4.1