This model is 23 months old. The same company has since released something newer: GPT-5.6-Cyber (2026-08-10). The details below are still accurate for this model — it just is not what we would recommend today.
o1-mini
OpenAI🇺🇸 United States
Compact reasoning model. Superseded by o3-mini and o4-mini.
Context window128K tokens
Input / 1M tokens$3
Output / 1M tokens$12
Version History
o1-mini-2024-09-12major
o1-mini debuts alongside o1-preview. Compact chain-of-thought model excelling at STEM tasks. 80% cheaper than o1-preview.
Benchmark Scores
Full leaderboard →1337.0 elo
Arena Elo