Loading...
Loading...
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 "high", "medium", or "low" to control the thinking time of the model. The default is "medium". OpenRouter also offers the model slug `openai/o3-mini-high` to default the parameter to "high". The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities. The model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.
Quality Index
25.9
132nd of 442
Top 30%
Coding Index
17.9
164th of 352
Top 47%
Price/1M
$1.93
537th cheapest
521% above median
Top 79%
Speed
155 tok/s
Top 12%
TTFT
6.72s
Context Window
200K
108th largest
Top 37%
Input
$1.10
per 1M tokens
Output
$4.40
per 1M tokens
Blended
$1.93
per 1M tokens
Cheaper than 21% of models. Median price is $0.31/1M tokens.
Daily
$1.93
Monthly
$57.75
155
tokens/sec
Faster than 88% of models
6.72
seconds
Faster than 8% of models
6.72
seconds
Faster than 24% of models
Market Median
46 tok/s
240% faster
Median TTFT
0.42s
1507% slower
Throughput/Dollar
80
tok/s per $/1M
Speed Comparison
Context Window
200K
tokens
Larger than 63% of models
Max Output
100K
tokens
50% of context