Announcing GPT-4o Mini: OpenAI’s Most Cost-Efficient Small Model

OpenAI is committed to making intelligence as broadly accessible as possible. Today, we’re excited to introduce GPT-4o mini, our most cost-efficient small model yet.

With GPT-4o mini, you can significantly expand the range of applications built with A…


This content originally appeared on DEV Community and was authored by Sooraj Suresh

OpenAI is committed to making intelligence as broadly accessible as possible. Today, we’re excited to introduce GPT-4o mini, our most cost-efficient small model yet.

With GPT-4o mini, you can significantly expand the range of applications built with AI, thanks to its affordability and efficiency. It scores 82% on MMLU and outperforms GPT-41 on chat preferences in the LMSYS leaderboard. At just 15 cents per million input tokens and 60 cents per million output tokens, GPT-4o mini is an order of magnitude more affordable than previous frontier models and over 60% cheaper than GPT-3.5 Turbo.

This model is perfect for enabling a broad range of tasks with low cost and latency, such as chaining or parallelizing multiple model calls, passing a large volume of context to the model, or interacting with customers through fast, real-time text responses. Today, GPT-4o mini supports text and vision in the API, with future support for text, image, video, and audio inputs and outputs. It has a context window of 128K tokens, supports up to 16K output tokens per request, and has knowledge up to October 2023. Thanks to the improved tokenizer shared with GPT-4o, handling non-English text is now even more cost-effective.

GPT-4o mini surpasses GPT-3.5 Turbo and other small models on academic benchmarks across textual intelligence and multimodal reasoning, and supports the same range of languages as GPT-4o. It also demonstrates strong performance in function calling, enabling developers to build applications that fetch data or take actions with external systems, and improved long-context performance compared to GPT-3.5 Turbo.

Here are some key benchmarks where GPT-4o mini excels:

• Reasoning tasks: GPT-4o mini scores 82.0% on MMLU, compared to 77.9% for Gemini Flash and 73.8% for Claude Haiku.
• Math and coding proficiency: GPT-4o mini excels in mathematical reasoning and coding tasks, scoring 87.0% on MGSM and 87.2% on HumanEval.
• Multimodal reasoning: GPT-4o mini scores 59.4% on MMMU, compared to 56.1% for Gemini Flash and 50.2% for Claude Haiku.

Discover how GPT-4o mini can transform your AI applications with its superior performance and affordability.


This content originally appeared on DEV Community and was authored by Sooraj Suresh


Print Share Comment Cite Upload Translate Updates
APA

Sooraj Suresh | Sciencx (2024-07-22T02:41:24+00:00) Announcing GPT-4o Mini: OpenAI’s Most Cost-Efficient Small Model. Retrieved from https://www.scien.cx/2024/07/22/announcing-gpt-4o-mini-openais-most-cost-efficient-small-model/

MLA
" » Announcing GPT-4o Mini: OpenAI’s Most Cost-Efficient Small Model." Sooraj Suresh | Sciencx - Monday July 22, 2024, https://www.scien.cx/2024/07/22/announcing-gpt-4o-mini-openais-most-cost-efficient-small-model/
HARVARD
Sooraj Suresh | Sciencx Monday July 22, 2024 » Announcing GPT-4o Mini: OpenAI’s Most Cost-Efficient Small Model., viewed ,<https://www.scien.cx/2024/07/22/announcing-gpt-4o-mini-openais-most-cost-efficient-small-model/>
VANCOUVER
Sooraj Suresh | Sciencx - » Announcing GPT-4o Mini: OpenAI’s Most Cost-Efficient Small Model. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2024/07/22/announcing-gpt-4o-mini-openais-most-cost-efficient-small-model/
CHICAGO
" » Announcing GPT-4o Mini: OpenAI’s Most Cost-Efficient Small Model." Sooraj Suresh | Sciencx - Accessed . https://www.scien.cx/2024/07/22/announcing-gpt-4o-mini-openais-most-cost-efficient-small-model/
IEEE
" » Announcing GPT-4o Mini: OpenAI’s Most Cost-Efficient Small Model." Sooraj Suresh | Sciencx [Online]. Available: https://www.scien.cx/2024/07/22/announcing-gpt-4o-mini-openais-most-cost-efficient-small-model/. [Accessed: ]
rf:citation
» Announcing GPT-4o Mini: OpenAI’s Most Cost-Efficient Small Model | Sooraj Suresh | Sciencx | https://www.scien.cx/2024/07/22/announcing-gpt-4o-mini-openais-most-cost-efficient-small-model/ |

Please log in to upload a file.




There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.