o1-mini vs o4-mini

Side by side pricing and context for o1-mini and o4-mini. Rates are curated catalog values with last verified dates on each model page.

o1-mini

Legacy compact OpenAI reasoning model for cheaper STEM-style tasks than full o1. Prefer o3-mini or o4-mini for new reasoning stacks when available.

Input $1.10 / Output $4.40 per 1M

Context 128K · Exact (o200k_base)

o4-mini

Smaller reasoning model when o3 is too expensive. Use for math, planning, and agent steps where you need chain-of-thought style work on a budget.

Input $1.10 / Output $4.40 per 1M

Context 200K · Exact (o200k_base)


Quick take

  • Input rates match on this snapshot.
  • Output rates match on this snapshot.
  • Both last verified on their model pages (2026-08-02 / 2026-08-02).

Rate table

Metrico1-minio4-mini
Input / 1M$1.10$1.10
Output / 1M$4.40$4.40
Cached input / 1Mn/a$0.275
Context128K200K
TokenizerExact (o200k_base)Exact (o200k_base)