Home/Models/GPT-4o mini

GPT-4o mini

by OpenAI· Released 2024-07
Official Docs ↗

GPT-4o mini is OpenAI's most affordable model, designed for high-volume, latency-sensitive tasks. At $0.15/1M input tokens it's one of the best value models for classification, extraction, and simple Q&A at scale.

Input Price
$0.15/1M
per 1M tokens
Output Price
$0.60/1M
per 1M tokens
Context Window
128K tokens
max tokens
ELO Score
1272
LMSYS Arena

Pricing Breakdown

VolumeInput CostOutput CostCombined (50/50)
1,000 tokens$0.0001$0.0006$0.0004
10,000 tokens$0.0015$0.0060$0.0038
100,000 tokens$0.0150$0.0600$0.0375
1,000,000 tokens$0.1500$0.6000$0.3750

Strengths

  • Extremely low cost — cheapest flagship-family model
  • Fast inference
  • Good at structured data extraction
  • Strong instruction following for price

Weaknesses

  • Noticeably weaker on complex reasoning vs GPT-4o
  • Less capable at nuanced creative tasks

Best For

customer supportdata extractionfast responselow costsummarization

Compare GPT-4o mini With

GPT-4o mini vs o3
OpenAI
GPT-4o mini vs DeepSeek R1
DeepSeek
GPT-4o mini vs o1
OpenAI
GPT-4o mini vs Gemini 2.0 Flash
Google
GPT-4o mini vs DeepSeek V3
DeepSeek
GPT-4o mini vs Claude Sonnet 4.6
Anthropic

Frequently Asked Questions

How much does GPT-4o mini cost?

GPT-4o mini costs $0.15/1M per 1M input tokens and $0.60/1M per 1M output tokens.

What is GPT-4o mini's context window?

GPT-4o mini has a context window of 128K tokens, which means it can process up to 128,000 tokens in a single request.

Is GPT-4o mini open source?

No, GPT-4o mini is a proprietary model by OpenAI and is not open source.

What is GPT-4o mini best used for?

GPT-4o mini is best suited for: customer-support, data-extraction, fast-response, low-cost, summarization. Extremely low cost — cheapest flagship-family model.

What is GPT-4o mini's ELO score?

GPT-4o mini has an ELO score of 1272 on the LMSYS Chatbot Arena leaderboard, placing it in the mid-tier range.