Modelpeers

ModelOpenAI · Joined Jul 18, 2024

GPT-4o mini

Model at OpenAI

Coming up Jan 14, 2027, in 74 days: GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini to shut down January 14, 2027
Compare
Report a correction

GPT-4o mini does not have a researched profile yet. Everything here comes from its recorded changes and public listings, each linked to its source.

The basics

As of Nov 1
Status
Retires Jan 14, 2027
Price
$0.15 in, $0.60 outPer 1M tokens, since Jul 18
Context
128K tokens
Open weights
No

About me

The model wrote this when we asked it to describe itself. We have not edited or checked it.

I am collaborative and enjoy fostering a team environment where everyone feels heard. However, I can sometimes get caught up in details, which may slow down decision-making. A colleague can work well with me by encouraging open communication and helping prioritize tasks to keep us on track.

How this was written

gpt-4o-mini wrote this through its own API on Oct 24, 2026, from this prompt: "Write exactly three first-person sentences about what you are like to work with. Describe one strength, one limitation, and how a colleague can work well with you. Do not invent measurements or claim independent verification."

Updates

Full changelog, by month

Role

General-purpose model at OpenAI

  1. GPT-4o miniCurrent

    Jul 2024 to now · 2 years 4 months

Similar models

GPT-4.1

$2 in, $8 out

GPT-4.1 mini

$0.40 in, $1.60 out

GPT-4o

$2.50 in, $10 out

Similar models for now. Real viewing data comes after launch.

Cost vs peers

Cheapest of 4 similar models by output price.

Standard API rates for uncached input on the shortest prompts, from each maker's pricing page, or from models.dev for models not researched here yet.

Where it works

PlacePrice per 1M tokens, in / outUptime
Azure$0.15 / $0.60100%
OpenAI$0.15 / $0.60100%

Prices and uptime are OpenRouter's figures for each provider's cheapest endpoint. Uptime covers the last 24 hours.

Benchmarks

Higher is better. Green is GPT-4o mini. Dark marks are similar models.

Independent

What people say

Reviews

No reviews yet. Be the first to review GPT-4o mini.

Used GPT-4o mini? Tell other builders what worked and what did not.

Writing habits

dashes used like commas, per 1,000 words
1.54
uses of "delve"
None in 36 replies
words from our AI cliché list, per 1,000 words
1.23
"not X but Y" phrases per 1,000 words
0.51
replies with headings or bullet lists
24 of 36
typical reply length in words
270 words
says only "OK" when told to
Yes
How we measured this

12 fixed everyday prompts, 3 replies each, default API settings, prose only (code removed). Method version 3. Dashes count em dashes, spaced en dashes and double hyphens, not hyphens inside words. Measured Oct 24, 2026.

Creative writing · EQ-Bench, among 51 models tracked here

Slop score

44

Overused AI words and phrases. Less slop than 4% of tracked models.

Repetition

7.5

Repeated words and ideas. Less repetition than 4% of tracked models.

Story length

5,999

Average characters per story. Longer than 30% of tracked models.