Back to all models
Get all the details on o4-mini, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as fine_tuning, function_calling, long_context, available API code samples, and performance strengths.
Key Metrics
Input Limit
200K tokens
Output Limit
100K tokens
Input Cost
$1.10/1M
Output Cost
$4.40/1M
Sample API Code
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="o4-mini",
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 |
|---|---|---|---|
1351 | OpenLLM Leaderboard | - | |
1093 | OpenLLM Leaderboard | - | |
1265 | OpenLLM Leaderboard | - | |
78.72 | LiveBench | High configuration | |
74.40 | LiveBench | Medium configuration | |
88.11 | LiveBench | High configuration | |
78.47 | LiveBench | Medium configuration | |
79.98 | LiveBench | High configuration | |
74.22 | LiveBench | Medium configuration | |
84.90 | LiveBench | High configuration | |
81.02 | LiveBench | Medium configuration | |
68.33 | LiveBench | High configuration | |
68.47 | LiveBench | Medium configuration | |
66.05 | LiveBench | High configuration | |
62.41 | LiveBench | Medium configuration | |
84.96 | LiveBench | High configuration | |
81.83 | LiveBench | Medium configuration | |
81.4% | Vellum | - | |
93.4% | Vellum | - | |
68.1% | Vellum | - | |
68.9% | Vellum | - | |
50% | Vellum | - |
Notes
Optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks. Part of the latest small o-series models.
Capabilities
fine tuning
function calling
long context
multimodal input
streaming
structured outputs
Supported Data Types
Input Types
text
image
Output Types
text
Strengths & Weaknesses
Exceptional at
coding tasks
visual tasks
high school math
Good at
fast reasoning
effective reasoning
general reasoning
instruction following
coding
data analysis
Additional Information
Latest Update
Apr 16, 2025
Knowledge Cutoff
Jun 1, 2024