ModelOpenAI · Joined Apr 14, 2025 · GPT-4.x

GPT-4.1 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

189th of 418 on Arena text
2nd cheapest of 4 similar models by price
0 incidents in the last 90 days

GPT-4.1 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: $0.40 in, $1.60 outPer 1M tokens, since Apr 14
Context: 1.05M tokens
Open weights: No

Updates

Oct 14

Retiring

GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini to shut down January 14, 2027

The remaining GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini snapshots, and fine-tunes built on them, will be removed on January 14, 2027, with gpt-6-luna as the replacement.

Takes effect Jan 14, 2027 · in 74 days

Action needed:: Migrate to gpt-6-luna before January 14, 2027 and re-test quality.

Full changelog, by month

Role

General-purpose model at OpenAI

Similar models

GPT-4.1

$2 in, $8 out

GPT-4o

$2.50 in, $10 out

gpt-4o-audio

Model

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

Cost vs peers

2nd cheapest of 4 similar models by output price.

GPT-4o mini$0.60 out · $0.15 in
GPT-4.1 mini$1.60 out · $0.40 in
GPT-4.1$8 out · $2 in
GPT-4o$10 out · $2.50 in

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

Place	Type	Price per 1M tokens, in / out	Uptime
Azure	API host	$0.40 / $1.60	99.65%
OpenAI	API host	$0.40 / $1.60	100%

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-4.1 mini. Dark marks are similar models.

Independent

What people say

Reviews

No reviews yet. Be the first to review GPT-4.1 mini.

Used GPT-4.1 mini? Tell other builders what worked and what did not.

Incidents

0 incidents in the last 90 days, from OpenAI's status page. Only major incidents or ones lasting 30 minutes or more are counted. Fewer records do not prove better uptime.

Jul 27OpenAI reported latency and timeouts on GPT-5.1 mini and GPT-4.1 mini2 h

Writing habits

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

Slop score

Overused AI words and phrases. Less slop than 8% of tracked models.

Repetition

5.7

Repeated words and ideas. Less repetition than 8% of tracked models.

Story length

5,606

Average characters per story. Longer than 6% of tracked models.