Back to all models
Get all the details on GPT-4o, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as multimodal_input, function_calling, structured_outputs, available API code samples, and performance strengths.
Key Metrics
Input Limit
128K tokens
Output Limit
16.4K tokens
Input Cost
$2.50/1M
Output Cost
$10.00/1M
Sample API Code
from openai import OpenAI;client = OpenAI();response = client.chat.completions.create(model='gpt-4o-2024-05-13',messages=[{'role': 'system', 'content': 'You are a helpful assistant.'},{'role': 'user', 'content': 'Hello!'}]);print(response.choices[0].message.content)
Required Libraries
openai
openai
Benchmarks
Benchmark | Score | Source | Notes |
---|---|---|---|
1282 | Open LLM Leaderboard | - | |
1206 | Open LLM Leaderboard | - | |
1000 | Open LLM Leaderboard | Score for api-gpt-4o-search, a search-optimized variant of GPT-4o. | |
72.08% | Vellum LLM Leaderboard | - | |
13.4% | Vellum LLM Leaderboard | - | |
56.1% | Vellum LLM Leaderboard | - | |
31% | Vellum LLM Leaderboard | - | |
60.3% | Vellum LLM Leaderboard | - | |
27.1% | Vellum LLM Leaderboard | - | |
53.95 | LiveBench | - | |
39.75 | LiveBench | - | |
69.29 | LiveBench | - | |
41.48 | LiveBench | - | |
63.53 | LiveBench | - | |
44.68 | LiveBench | - | |
64.94 | LiveBench | - |
Notes
GPT-4o (“o” for “omni”) is OpenAI's versatile, high-intelligence flagship model. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is the best model for most tasks, and is the most capable model outside of the o-series models.
Supported Data Types
Input Types
text
image
Output Types
text
Strengths & Weaknesses
Exceptional at
high intelligence
versatility
multimodal understanding
general reasoning
instruction following
vision tasks
Good at
structured outputs
function calling
code interpretation
web browsing
file search
Additional Information
Latest Update
May 13, 2024
Knowledge Cutoff
Oct 1, 2023