About
OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...
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
Grok 3Q:0.0
$8.00+316%
Seed-OSS-36B-InstructQ:-0.1
$0.30-84%
Nova 2.0 Lite (high)Q:-0.2
$0.85-56%
Qwen3 235B A22B 2507 InstructQ:-0.2
$0.36-82%
Performance
223
tokens/sec
Faster than 91% of models
17.06
seconds
Faster than 6% of models
17.06
seconds
Faster than 29% of models
Market Median
94 tok/s
137% faster
Median TTFT
1.11s
1433% slower
Throughput/Dollar
116
tok/s per $/1M
Speed Comparison
Qwen3 0.6B (Reasoning)
224 tok/s+0%
Nova 2.0 Lite (Non-reasoning)
224 tok/s+0%
OpenAI: GPT-4o
222 tok/s-0%
Context Window
200K
tokens
Larger than 50% of models
Max Output
100K
tokens
50% of context
Benchmarks
MMLU-Pro
80.2%
GPQA Diamond
77.3%
HLE
12.3%
LiveCodeBench
73.4%
SciCode
39.8%
TerminalBench Hard
6.1%
MATH-500
98.5%
AIME
86.0%
AIME 2025Not evaluated
IFBench
67.1%
Long Context Recall
39.3%
Tau2
31.3%
Market AverageTop Score