Back to all models
Get all the details on GPT-4, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as fine_tuning, streaming, available API code samples, and performance strengths.
Key Metrics
Input Limit
8.2K tokens
Output Limit
8.2K tokens
Input Cost
$30.00/1M
Output Cost
$60.00/1M
Sample API Code
from openai import OpenAI
client = OpenAI()
chat_completion = client.chat.completions.create(
messages=[
{
"role": "user",
"content": "Say this is a test",
}
],
model="gpt-4",
)
print(chat_completion.choices[0].message.content)Required Libraries
openai
openai
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1186 | OpenLM Arena | Score for gpt-4-0314 snapshot | |
1163 | OpenLM Arena | Score for gpt-4-0613 snapshot, which the gpt-4 alias currently points to |
Notes
An older version of a high-intelligence GPT model, usable in Chat Completions.
Capabilities
fine tuning
streaming
Supported Data Types
Input Types
text
Output Types
text
Strengths & Weaknesses
Good at
general reasoning
instruction following
Poor at
speed
cost
Additional Information
Latest Update
Dec 1, 2023
Knowledge Cutoff
Dec 1, 2023