GPT-4o-mini

OPENAI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1489Aider: 40.6%

Max Context Limit128,000Max Out: 16,384 tokens

Prompt Caching50% OFF$0.07 / 1M cached

Standard API / 1M$0.75Blended Standard Rate

Model Capabilities & Contract SLAs

Coding & Logic
Fictional
Drafting
Classification
Conversational
Agentic
📋 Strict JSON Schema
🛠️ Native Tool Calling

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.15 / 1M

⚡ Cached Input (Prompt Cache Read)50% OFF$0.07 / 1M

Output Tokens (Completion)$0.60 / 1M

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

Evaluate Competitors

VS Engine MatchupGPT-4o-mini vs OpenAI: GPT-5.4 Pro (batch)VS Engine MatchupGPT-4o-mini vs OpenAI: GPT-5.1-Codex-Mini VS Engine MatchupGPT-4o-mini vs OpenAI: GPT-5 Mini VS Engine MatchupGPT-4o-mini vs OpenAI: GPT-4o (batch)VS Engine MatchupGPT-4o-mini vs Google: Gemini 3.1 Pro Preview (batch)VS Engine MatchupGPT-4o-mini vs OpenAI: GPT-5.2 (batch)