OpenAIOpenAI

GPT-4o

Multimodal flagship — text, vision, and audio

GPT-4o ('o' for omni) is OpenAI's multimodal model that processes text, images, and audio natively. It matches GPT-4 Turbo on text tasks while being twice as fast and half the price.

Try GPT-4o

Specifications

Context window128k tokens
Input price$2.50 / 1M tokens
Output price$10.00 / 1M tokens
Credits per query3 cr
Released2024-05
LicenseProprietary

Features

VisionTool useJSON modeFunction callingCode

Benchmark Scores

What do these mean?

Sourced from official model cards and academic papers. Higher is better.

PhD-level science & reasoning

53.6%

Mathematical olympiad problems

Chatbot Arena human preference ranking

1285

Python coding — pass@1 rate

90.2%

Competition-level mathematics

76.6%

General knowledge across 57 academic domains

87.2%

Multi-turn instruction following (out of 10)

9/10

Real-world GitHub issue resolution rate