Model
Model explorer

OpenAI o1-mini

CLOSED
OpenAI · o1 family · released Sep 12, 2024

Cost-efficient STEM/coding reasoning model; retired from OpenAI's API on 2025-10-27.

ReasoningCodingVisionFunction callingTool useAgentic
1261.7
Elo · rank #164
Parameters
Undisclosed
Active params
—
Context
128K tokens
Architecture
Dense transformer reasoning model (size undisclosed)
License
Proprietary
Languages
—
API price (in/out)
$3 / $12
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
AIMEMath70.0%#106
best: GPT-5.2 · 100.0%
CodeforcesCoding1650#33
best: DeepSeek-V4-Pro (Think Max) · 3206
DROPReasoning83.9#16
best: Hunyuan-T1 · 93.1
GPQA DiamondReasoning60.0%#166
best: GPT-5.6 · 94.6%
HumanEvalCoding92.4%#11
best: Claude Opus 4.5 · 99.4%
MATH-500Math90.0%#48
best: GPT-5 · 99.4%
MGSMMath89.9%#13
best: OpenAI o4-mini · 93.7%
MMLUKnowledge85.2%#58
best: OpenAI o3 · 92.9%
SimpleQAKnowledge7.6%#43
best: GPT-4.5 · 62.5%
Run it locally
Closed weights — available via API only. No local deployment.
Input / M tok
$3
Output / M tok
$12
o1 family
Elo progression across releases
OpenAI o1-miniSep 20241261.7OpenAI o1-previewSep 20241380.6OpenAI o1Dec 20241582.8OpenAI o1-proDec 20241700.4
Resources
DOCSdevelopers.openai.com/api/docs/models/o1-mini
API price $3/$12 · each benchmark row carries its own source badge (see methodology)