Back to all models
Get all the details on GPT-4.1, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as distillation, fine_tuning, function_calling, available API code samples, and performance strengths.
Key Metrics
Input Limit
1.0M tokens
Output Limit
32.8K tokens
Input Cost
$2.00/1M
Output Cost
$8.00/1M
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-4.1",
)Required Libraries
openai
openai
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1366 | OpenLLM Leaderboard | - | |
1261 | OpenLLM Leaderboard | - | |
1281 | OpenLLM Leaderboard | - | |
62.99 | LiveBench | - | |
44.39 | LiveBench | - | |
73.19 | LiveBench | - | |
62.39 | LiveBench | - | |
66.40 | LiveBench | - | |
54.55 | LiveBench | - | |
77.05 | LiveBench | - | |
66.3 | Vellum Leaderboard | % | |
55 | Vellum Leaderboard | % | |
48.1 | Vellum Leaderboard | % |
Notes
Flagship GPT model for complex tasks. It is well suited for problem solving across domains.
Capabilities
distillation
fine tuning
function calling
long context
multimodal input
predicted outputs
snapshots
streaming
structured outputs
vision
web browsing via tool
Supported Data Types
Input Types
text
image
Output Types
text
Strengths & Weaknesses
Exceptional at
complex reasoning
problem solving
Good at
coding tasks
data analysis
instruction following
multimodal understanding
web development tasks
Additional Information
Latest Update
Apr 14, 2025
Knowledge Cutoff
Jun 1, 2024