OpenAI: o4 Mini High

File input Text input Image input Text output
Author's Description

OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains. Despite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.

Key Specifications
Cost
$$$$$
Context
200K
Released
Apr 16, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tool Choice Include Reasoning Response Format Structured Outputs Reasoning Tools Max Tokens Seed
Features

This model supports the following features:

Reasoning Response Format Tools Structured Outputs
Performance Summary

OpenAI o4 Mini High, released on April 16, 2025, is a compact yet powerful reasoning model designed for efficiency and strong multimodal capabilities. It exhibits moderate speed performance, ranking in the 31st percentile, and is positioned at premium pricing levels, falling into the 14th percentile. A standout feature is its exceptional reliability, boasting a 100% success rate across all benchmarks, indicating minimal technical failures. The model demonstrates remarkable accuracy in several key areas. It achieved perfect accuracy in General Knowledge, making it the most accurate model at its price point and speed. Its reasoning capabilities are strong, scoring 98.0% accuracy and ranking in the 92nd percentile. Similarly, it performs well in Email Classification (99.0% accuracy, 77th percentile) and Coding (93.0% accuracy, 85th percentile). The model also shows high accuracy in Ethics (98.0%). However, a notable weakness is its performance in the Hallucinations Baseline, where it scored only 62.0% accuracy, placing it in the 13th percentile. While its Instruction Following accuracy is decent at 71.0%, its cost for this task is relatively high. Overall, o4 Mini High excels in complex problem-solving, coding, and general knowledge, making it suitable for high-throughput scenarios where reliability and strong reasoning are paramount, despite its premium cost and moderate speed.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1.1
Completion $4.4
Input Cache Read $0.275
Web Search $10000

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/o4-mini-high-2025-04-16 200K $1.1 / 1M tokens $4.4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai