Announcing GPT-4o mini: Most cost-efficient small model

We're excited to announce GPT-4o mini, our most cost-efficient small model. It's priced at 15 cents per million input tokens and 60 cents per million output tokens, making it significantly cheaper than previous models.

Key highlights

• Scores 82% on MMLU, outperforming GPT-3.5 Turbo and comparable to GPT-4 on many benchmarks
• 128K context window
• Support for text, vision, and function calling
• Available now in the API

To get started:

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}]
)

Check the documentation for full details. Let us know your feedback!