Private AI
The cheaper version of OpenAI's newest thinking model. Fast, cheap, and with a maximum output of 100,000 words.
Context Window
200.0K
Max Output
100.0K
Input Price (Auto)
$1.10/1M
Output Price (Auto)
$4.40/1M
Cache Read (Auto)
$0.55/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
25.9
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
17.9
GPQA Diamond
Graduate-level scientific reasoning
74.8%
Better than 63% of models compared
HLE
Humanity's Last Exam
8.7%
Better than 61% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
28.7%
Better than 35% of models compared
SciCode
Python programming for scientific computing
39.9%
Better than 75% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
6.8%
AIME
American Invitational Mathematics Examination
77.0%
Better than 86% of models compared
Math-500
Diverse mathematical problem solving benchmark
97.3%
Better than 88% of models compared
MMLU-Pro
Professional and academic subject knowledge
79.1%
Better than 63% of models compared
Last updated Jun 4, 2026
Artificial AnalysisBetter than 36% of models compared
LiveCodeBench
Contamination-free coding benchmark
71.7%
Better than 82% of models compared
