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()

completion = client.chat.completions.create(
  model="o1-mini",
  messages=[
    {"role": "user", "content": "Tell me about o1-mini."}
  ]
)

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

Required Libraries

openai
@openai/openai-node

Notes

A small model alternative to o1. o1-mini is a faster and more affordable reasoning model, but the newer o3-mini model is recommended as it features higher intelligence at the same latency and price. The 'o1-mini' alias currently points to the 'o1-mini-2024-09-12' snapshot, which is deprecated. Supports reasoning tokens.

Capabilities

Reasoning
Streaming
Text input
Text output
Chat Completions API

Supported Data Types

Input Types

Text

Output Types

Text

Strengths & Weaknesses

Exceptional at

Reasoning

Good at

Affordability

Poor at

Speed (relative to other factors, labeled 'Slow' in UI)
Function calling
Structured outputs
Fine-tuning
Distillation
Predicted outputs

Additional Information

Latest Update

Sep 12, 2024

Knowledge Cutoff

2023-10-01

ELO Score

1304