←All models
Directory · Models · OpenAI
o-serieso4
Deep-reasoning model. Spends more tokens thinking to crush math, science, and hard coding problems.
Input / 1M
$15.00
Output / 1M
$60.00
Context
200K
Released
Feb 18, 2026
Benchmark profile
Profile
MMLU-Pro93.8%
HumanEval92.3%
SWE-Bench68.0%
MATH96.2%
GPQA82.5%
ARC-AGI96.2%
Scores
Editorial
Strengths
- +State-of-the-art math and science
- +Extremely high-ceiling reasoning
Trade-offs
- −Slow and expensive; not for chat
Price history (last 90 days)
Input / 1M
Output / 1M
What this costs to use
All task cards →Recommended alternatives
Where to buy
All providers →Input pricing · $/1M tokens · sorted cheapest first