The Open-Source AI Stack
RSS
All models

Models · o-series

OpenAI o3-mini

Proprietary OpenAI · 2025-01-31 · Proprietary

Released January 31, 2025 as a smaller, faster o-series reasoning model with three selectable effort levels (low, medium, high). Positioned by OpenAI as a specialized alternative to o1 for technical domains requiring precision and speed at a fraction of o1's cost.

Cost

$1.10 / Mtok input
$4.40 / Mtok output

OpenAI API · as of 2026-05-21

source ↗

Speed

145.3 tok/sec output
8257 ms TTFT

· as of 2026-05-21

source ↗

Architecture

tokens in Embedding vocab not disclosed × N layers Architecture not disclosed (proprietary or undocumented) Output projection tokens out
Schema-generated from data/models.yaml. Every label is auditable against the model's sources.

Specs

Architecture
unknown
Total params
not disclosed
Active params
not disclosed
Context window
200K tokens
Attention
unknown
Position encoding
unknown
Post-training
rlhf
OSI-approved
no
Data released
no
Training code
not released

Benchmarks

Each score carries the date it was published; we never infer or interpolate missing scores.

General reasoning

MMLU-Pro 79.1 as of 2026-05-21 source ↗
GPQA-Diamond 79.7 as of 2025-01-31 source ↗

Code

SWE-Bench Verified 49.3 as of 2025-01-31 source ↗
LiveCodeBench 71.7 as of 2026-05-21 source ↗

Math

MATH 97.3 as of 2026-05-21 source ↗
AIME 2024 87.3 as of 2025-01-31 source ↗

Available quantizations

None. The weights are not distributed, so there are no public quantizations.

Notable innovations

  • · Selectable reasoning effort levels exposed in the API
  • · First o-series model offered at sub-$5 per million output tokens

Sources