Logo
Back to all models

o1-mini - In-Depth Overview

OpenAI · o1

Current

Get all the details on o1-mini, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as reasoning, streaming, available API code samples, and performance strengths.

Key Metrics

Input Limit

128K tokens

Output Limit

65.5K tokens

Input Cost

$1.10/1M

Output Cost

$4.40/1M

Sample API Code

from openai import OpenAI

client = OpenAI()

chat_completion = client.chat.completions.create(
    messages=[
        {
            'role': 'user',
            'content': 'Hello world!',
        }
    ],
    model='o1-mini',
)

print(chat_completion.choices[0].message.content)

Required Libraries

openai
openai

Benchmarks

BenchmarkScoreSourceNotes
1304
lmarena.ai-
1042
lmarena.ai-
63.6
Vellum-
60
Vellum-
90
Vellum-
52.2
Vellum-
32.9
Vellum-

Notes

A small model alternative to o1. Faster and more affordable reasoning model than o1, but o3-mini is recommended for higher intelligence at the same latency and price. Fine-tuning, function calling, and structured outputs are not supported.

Capabilities

reasoning
streaming

Supported Data Types

Input Types

text

Output Types

text

Strengths & Weaknesses

Good at

Reasoning
Cost-effectiveness (compared to o1)
Speed (compared to o1)

Additional Information

Latest Update

Sep 12, 2024

Knowledge Cutoff

Oct 1, 2023