OpenAI · o-serie

o4-mini

Current · Released: June 1, 2025

Context window
200.000 tokens
Max output
65.536 tokens
Price input / 1M tokens
$1.10
Price output / 1M tokens
$4.40
Price cache-read / 1M
$0.28

Capabilities

  • Reasoning
  • Code
  • Wiskunde
  • Tool use

Benchmark scores

MMMU
81.6
AIME 2025
92.7
MathVista
84.3
Codeforces
2,719.0
GPQA Diamond
81.4
SWE-bench Verified
68.1

What do these benchmarks mean? →

Notes

Compact reasoning model from the o-series. Strong price-to-performance for AIME and coding. Source: openai.com/api/pricing.