GPT-4o mini at a glance
GPT-4o mini scored 82% on MMLU, beat GPT-3.5 Turbo and other small models on OpenAI's benchmarks, and cost $0.15/$0.60 per 1M tokens with a 128K context window.
What changed with GPT-4o mini
OpenAI announced GPT-4o mini on July 18, 2024, as its most cost-efficient small model. It cost 15 cents per million input tokens and 60 cents per million output tokens, had a 128K-token context window with up to 16K output tokens, and knowledge up to October 2023.
OpenAI reported 82.0% on MMLU, 87.0% on MGSM and 87.2% on HumanEval, ahead of Gemini Flash and Claude Haiku in its comparisons. It launched with text and vision in the API, and it was the first OpenAI API model to use the instruction hierarchy method meant to resist prompt injection and jailbreaks.
GPT-4o mini benchmarks and pricing
Values are copied from the linked source on the date shown. They are not IA Compa measurements.
- Input price per 1M tokensas of · Source for Input price per 1M tokens: openai.com (opens in a new tab)
- $0.15
- Output price per 1M tokensas of · Source for Output price per 1M tokens: openai.com (opens in a new tab)
- $0.60
- Context windowas of · Source for Context window: openai.com (opens in a new tab)
- 128K tokens
How it compares
Models that were current when this was published (released in the six months before it, newest version of each line), so these figures are from that time. Under each chart is the current best. (Models)
Current best (as of Nov 6, 2026): Claude Haiku 5.5, $0.10
Current best (as of Nov 6, 2026): Claude Haiku 5.5, $0.50
Current best (as of Nov 6, 2026): GPT-6 Cyber, 1.05M tokens
Where to compare GPT-4o mini
Independent leaderboards and official resources for comparing this model yourself. Rankings change often; each site shows its own current data.
General leaderboards
Official resources
Why GPT-4o mini matters for businesses
For businesses, GPT-4o mini replaced GPT-3.5 Turbo as the workhorse for high-volume tasks such as support chat, data extraction and classification. Launch partners Ramp and Superhuman used it for receipts and email replies.
Sources for this story
- GPT-4o mini: advancing cost-efficient intelligence (opens in a new tab)Official
OpenAI · openai.com
- GPT-4o mini (archived July 19, 2024) (opens in a new tab)Official
OpenAI via Internet Archive · web.archive.org
- GPT-4o mini model page (opens in a new tab)Benchmark
Artificial Analysis · artificialanalysis.ai
Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.
- #llm
- #openai
- #gpt-4o
- #small-model
- #pricing
