About
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...
Related Models
Pricing
Input
$1.10
per 1M tokens
Output
$4.40
per 1M tokens
Blended
$1.93
per 1M tokens
Cheaper than 25% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.93
Monthly
$57.75
vs. Similar Models
GPT-5 nano (medium)Q:0.0
$0.14-93%
Nova 2.0 Lite (medium)Q:0.0
$0.85-56%
Qwen3.5 Omni FlashQ:0.0
$0.28-86%
OpenAI: o1-proQ:-0.1
$262.50+13536%
Performance
221
tokens/sec
Faster than 91% of models
5.14
seconds
Faster than 17% of models
5.14
seconds
Faster than 47% of models
Market Median
94 tok/s
136% faster
Median TTFT
1.10s
366% slower
Throughput/Dollar
115
tok/s per $/1M
Speed Comparison
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
220 tok/s-0%
Qwen3 0.6B (Non-reasoning)
222 tok/s+0%
Nova 2.0 Lite (Non-reasoning)
219 tok/s-1%
Context Window
200K
tokens
Larger than 50% of models
Max Output
100K
tokens
50% of context
Benchmarks
MMLU-Pro
79.1%
GPQA Diamond
74.8%
HLE
8.7%
LiveCodeBench
71.7%
SciCode
39.9%
TerminalBench Hard
6.8%
MATH-500
97.3%
AIME
77.0%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2
28.7%
Market AverageTop Score