GPT-4o is OpenAI's flagship omni model announced on May 13, 2024. OpenAI describes it as reasoning across audio, vision, and text in real time, accepting combinations of text, audio, image, and video inputs and generating text, audio, and image outputs; the OpenAI API model page lists GPT-4o with a 128,000-token context window.
Pricing
Model profile · Current snapshot
Input / 1M
$2.50
Output / 1M
$10.00
Blended / 1M
$4.38
Output TPS
0
TTFT (s)
0
Model Intelligence
Context window
128,000 tokens
Arena ranking
11
Benchmarkable
Yes
Model level
release
Intelligence Index
11.1
Math Index
6
MMLU Pro
0.75
GPQA
0.54
HLE
0.02
LiveCodeBench
0.31
SciCode
0.33
MATH-500
0.76
AIME
0.15
AIME 2025
0.06
IFBench
0.34
LCR
0
TerminalBench Hard
0.08
TAU2
0.25
Recent stories
0 linked stories
No linked stories yet.