OpenAI: o3 Mini High

Text input Text output
Author's Description

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 coding. 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.

Key Specifications
Cost
$$$$$
Context
200K
Parameters
200B
Released
Feb 12, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tool Choice Max Tokens Structured Outputs Tools Seed Response Format
Features

This model supports the following features:

Structured Outputs Response Format Tools
Performance Summary

OpenAI o3-mini-high, released on February 12, 2025, is a specialized language model designed for STEM reasoning, building upon the o3-mini with enhanced reasoning effort. It exhibits moderate speed performance, ranking in the 24th percentile across benchmarks, and is positioned at premium pricing levels, falling into the 12th percentile for cost. A standout feature is its exceptional reliability, achieving the 100th percentile with minimal technical failures, ensuring consistent response delivery. The model demonstrates strong performance across various benchmarks. It excels in Reasoning (98.0% accuracy, 94th percentile) and Coding (90.0% accuracy, 80th percentile), aligning with its STEM optimization. Its General Knowledge is perfect at 100.0% accuracy, notably being the most accurate model at its price point and among models of similar speed. While Instruction Following shows solid accuracy (62.0%, 72nd percentile), Email Classification (97.0%, 47th percentile) and Ethics (98.0%, 40th percentile) are competent but not top-tier compared to other models in their respective categories. Key strengths include its robust reasoning capabilities, high accuracy in coding and general knowledge, and unparalleled reliability. Its primary weakness lies in its premium pricing, which may be a consideration for cost-sensitive applications despite its performance.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1.1
Completion $4.4
Input Cache Read $0.55

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/o3-mini-high-2025-01-31 200K $1.1 / 1M tokens $4.4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by openai