Logo
Back to all models

ChatGPT-4o - In-Depth Overview

OpenAI · GPT-4o

Current
Flagship
Latest in family

Model ID: chatgpt-4o

Get all the details on ChatGPT-4o, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as file_inputs, web_browsing_via_tool, code_interpretation, available API code samples, and performance strengths.

Key Metrics

Input Limit

128K tokens

Output Limit

4.1K tokens

Input Cost

$5.00/1M

Output Cost

$15.00/1M

Sample API Code

from openai import OpenAI;client = OpenAI();response = client.chat.completions.create(model="chatgpt-4o",messages=[{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello!"}]);print(response.choices[0].message.content)

Required Libraries

openai
openai

Benchmarks

BenchmarkScoreSourceNotes
1405
Open LLM LeaderboardScore for chatgpt-4o-latest-20250326
964
Open LLM LeaderboardScore for GPT-4o-2024-11-20, a related model variant.
1310
Open LLM LeaderboardScore for chatgpt-4o-latest-20250326
1000
Open LLM LeaderboardScore for api-gpt-4o-search, a search-optimized variant.
61.65
LiveBench-
48.81
LiveBench-
77.48
LiveBench-
55.72
LiveBench-
66.52
LiveBench-
49.43
LiveBench-
71.92
LiveBench-
72.08%
Vellum LLM LeaderboardScore for GPT-4o, the base model.
13.4%
Vellum LLM LeaderboardScore for GPT-4o, the base model.
56.1%
Vellum LLM LeaderboardScore for GPT-4o, the base model.
31%
Vellum LLM LeaderboardScore for GPT-4o, the base model.
60.3%
Vellum LLM LeaderboardScore for GPT-4o, the base model.
27.1%
Vellum LLM LeaderboardScore for GPT-4o, the base model.

Notes

ChatGPT-4o is the GPT-4o model used in ChatGPT, offering fast, intelligent, and flexible capabilities with multimodal inputs and outputs.

Supported Data Types

Input Types

text
image
audio

Output Types

text
audio

Strengths & Weaknesses

Exceptional at

text understanding
vision tasks
code generation

Good at

general reasoning
instruction following

Poor at

mathematics

Additional Information

Latest Update

Mar 26, 2025

Knowledge Cutoff

Oct 1, 2023