Responsible AI Use Disclaimer: The tools listed are for informational purposes. Users are responsible for adhering to ethical guidelines. Learn more.

OpenAI ProprietaryJul 2024

GPT-4o mini

Cheap, fast, and still surprisingly capable — OpenAI’s budget tier.

Intelligence index
56/ 100
vs all models9th pctile
Composite of MMLU, GPQA, MATH & HumanEval
Speed
145tok/s
vs all models73th pctile
Median across providers, steady state
Blended price
$0.26/ 1M tokens
vs all models91th pctile
3:1 input:output blend

At a glance

Context window
128k tokens
Max output
16k tokens
Input price
$0.15 / 1M tokens
Output price
$0.60 / 1M tokens
Time to first token
0.32s
Input modalities
text, image
Output modalities
text
License
Proprietary
Provider
OpenAI

Benchmark scores

Public scores from each provider; bars compare this model against the leader in each benchmark.

MMLU
General knowledge across 57 subjects
82.0
leader: 91.8
MMLU Pro
Harder MMLU successor with more reasoning
61.0
leader: 80.0
GPQA
Graduate-level science Q&A
40.2
leader: 78.0
MATH
Competition mathematics
70.0
leader: 94.8
HumanEval
Python code generation pass@1
87.2
leader: 95.8
Strengths
  • Cheapest OpenAI model
  • Fast
  • Vision included
Weaknesses
  • Falls behind on reasoning and code
Best for
  • High-volume tasks
  • Cost-sensitive APIs

GPT-4o mini vs… popular head-to-heads

One-click matchups against the models people compare GPT-4o mini with most.

GPT-4o mini — frequently asked questions

GPT-4o mini is a large language model from OpenAI, released on 18 July 2024. Cheap, fast, and still surprisingly capable — OpenAI’s budget tier.

Need help choosing between models?

Compare every option in one sortable table — intelligence, speed and price on a single page.