Models · GPT-4o
MODEL REGISTRY

GPT-4o

OpenAI's multimodal flagship. Accepts text, image, and audio input; generates text and audio output. Replaced GPT-4 Turbo as the default model.

OpenAI CLOSED RELEASED May 13, 2024 ACTIVE
CONTEXT
128K
tokens
PARAMETERS
---
total
BENCHMARKS
3
tracked
INPUT
$2.5
per 1M tokens
OUTPUT
$10
per 1M tokens
Specifications
Lab OpenAI
Type CLOSED
Released May 13, 2024
Context Window 128K tokens
Training Cutoff 2023-10
Status ACTIVE
Pricing
INPUT
$2.50
per 1M tokens
OUTPUT
$10.00
per 1M tokens
Benchmarks 3 tracked
Benchmark Score Date
MMLU
88.7 2024-05
HumanEval
90.2 2024-05
MATH
76.6 2024-05
Capabilities 5
textvisionaudiofunction-callingjson-mode
About

GPT-4o (“o” for “omni”) is OpenAI’s multimodal model, processing and generating text, images, and audio natively within a single architecture. It matches GPT-4 Turbo performance on text and code while being faster and cheaper.