Introducing GPT-4o MiniOpenAIReleased July 18, 2024

GPT-4o Mini

High-speed, cost-efficient small model outperforming GPT-3.5 Turbo across every dimension for 15 cents per million tokens.

text-to-textProprietary API$0.15 / 1M tok (High Speed)Context: 128K (128,000 tokens)Arena ELO: 1270

Technical Specifications

Architecture Type
Compact Omnimodal Transformer
Total Parameters
Compact Tier
Context Window
128K (128,000 tokens)
Max Output Tokens
16.384K (16,384 tokens)
Knowledge Cutoff
October 2023
Supported Modalities
text, code, vision
License & Access
OpenAI Business Terms

Benchmark Evaluations

Math
70.2
Mgsm
87
Mmlu
82
Humaneval
87
Chatbot Arena ELO
1270

Deep Architectural Overview

GPT-4o Mini democratized frontier intelligence by pricing input tokens at $0.15/1M. With 82% MMLU and vision support, it quickly became the primary engine for high-throughput customer service, data extraction, and mobile applications.

Strengths & Considerations

Core Strengths
  • 60% cheaper than GPT-3.5 Turbo
  • MMLU score of 82.0%
  • Full 128k context with 16k output capacity
Known Limitations
  • Complex multi-agent orchestration trails GPT-4o

Token & API Pricing

Input Tokens (1M)$0.15
Output Tokens (1M)$0.60
Cached Input (1M)$0.0750
Pricing is verified directly against OpenAI's developer documentation and API rate sheets.

Similar & Alternative Models

Explore other frontier models from OpenAI and comparable reasoning engines.

Browse all models
OpenAI

OpenAI GPT-6 model for focused, high-volume workloads where cost efficiency is the priority.

1.05M ctxUSD 0.10 / 1M input tok; USD 0.50 / 1M output tok
OpenAI

OpenAI GPT-6 model built for complex coding and agentic workflows, balancing intelligence and cost.

1.05M ctxUSD 2 / 1M input tok; USD 10 / 1M output tok
OpenAI

OpenAI’s premier sixth-generation frontier model, built for the most demanding end-to-end software engineering and scientific research tasks.

1.05M ctx$10.00 / 1M tok (GPT-6 Frontier)