o3 Mini High

OPENAI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1490Chatbot Arena Verified

Max Context Limit200,000Max Out: 100,000 tokens

Prompt Caching50% OFF$0.55 / 1M cached

Standard API / 1M$5.50🧠 Deep Reasoner

Model Capabilities & Contract SLAs

Coding & Logic
Reasoning
Drafting
Classification
Agentic
Fictional
📋 Strict JSON Schema
🛠️ Native Tool Calling
🧠 Extended Test-Time Reasoning

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...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$1.10 / 1M

⚡ Cached Input (Prompt Cache Read)50% OFF$0.55 / 1M

Output Tokens (Completion)$4.40 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine Matchupo3 Mini High vs OpenAI: GPT-5.2 (batch)VS Engine Matchupo3 Mini High vs OpenAI: GPT-5.1 (batch)VS Engine Matchupo3 Mini High vs OpenAI: GPT-5 Pro VS Engine Matchupo3 Mini High vs OpenAI: GPT-5 (batch)VS Engine Matchupo3 Mini High vs OpenAI: GPT-5 Mini (batch)VS Engine Matchupo3 Mini High vs Qwen: Qwen2.5 VL 72B Instruct