Side by side pricing and context for o1 and o3. Rates are curated catalog values with last verified dates on each model page.
o1
Legacy high-cost OpenAI reasoning model kept for historical budget comparisons. Prefer o3 or GPT-5 reasoning paths for new work unless you are pinned to o1.
Input $15.00 / Output $60.00 per 1M
Context 200K · Exact (o200k_base)
o3
OpenAI reasoning model for harder problems where extra thinking tokens are worth the bill. Watch output cost: reasoning tokens are billed at the output rate.
Input $2.00 / Output $8.00 per 1M
Context 200K · Exact (o200k_base)
Quick take
- o3 is cheaper on input in this catalog snapshot.
- o3 is cheaper on output in this catalog snapshot.
- Both last verified on their model pages (2026-08-02 / 2026-08-02).
Rate table
| Metric | o1 | o3 |
|---|---|---|
| Input / 1M | $15.00 | $2.00 |
| Output / 1M | $60.00 | $8.00 |
| Cached input / 1M | $7.50 | $0.500 |
| Context | 200K | 200K |
| Tokenizer | Exact (o200k_base) | Exact (o200k_base) |