GPT-4o

Aug '24

Creator

OpenAI

Released

2024-08-06

Intelligence

9.6

Artificial Analysis Index

Coding

Artificial Analysis Index

In $/1M

$2.50

input tokens

Out $/1M

$10.00

output tokens

Blended $/1M

$4.38

3:1 blended

Speed

0

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

Proprietary

non-commercial

Weights

Closed

API only

Modalities

Image · Text

Parameters

GPT-4o ('o' for 'omni') is a multimodal AI model that accepts text, audio, image, and video inputs, and generates text, audio, and image outputs. It matches GPT-4 Turbo performance on text and code, with improvements in non-English languages, vision, and audio understanding.

Capability profile

Category strength across 20 domains, via LLM Stats.

image to text
90legal
80finance
80vision
70biology
70physics
70language
70chemistry
70healthcare
70multimodal
70instruction following
70writing
60
long context
60structured output
60math
50general
50reasoning
50tool calling
50communication
50factuality
40spatial reasoning
40code
30frontend development
30
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
52
Humanity’s Last Exam
3
MMLU-Pro
SciCode
33
LiveCodeBench
32
MATH-500
79
AIME 2025
τ²-Bench (agentic)
29
Terminal-Bench Hard
8
IFBench
36
Via Artificial Analysis

Providers

Inference hosts serving this model — their own pricing and measured performance, cheapest input first.

ProviderIn $/1MOut $/1MThroughputLatencyStatus
Azure$2.50$10.00990.53active
OpenAI$2.50$10.001320.50active
All providers

2 hosts · via LLM Stats

© 2026 NYSGPT2525 LLC