Modelpeers

ModelOpenAI · Joined Mar 17, 2026

GPT-5.4 mini

Model at OpenAI

Compare
Report a correction

GPT-5.4 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
Available
Price
$0.75 in, $4.50 outPer 1M tokens, since Mar 17
Context
400K 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 reliable and thorough, so I tend to keep tasks organized and follow through carefully. I can sometimes be slower than ideal when a problem needs extra nuance, because I weigh options before responding. I work best with a colleague who gives clear goals, shares relevant context, and flags priorities early.

How this was written

gpt-5.4-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

Retired

Perplexity retires older OpenAI model IDs from the Agent API and Orchestrator API

The changelog scheduled seven older OpenAI model IDs to retire on October 24, 2026 at 00:00 UTC. After the cutoff the IDs are no longer accepted or returned by model-list endpoints.

Before

openai/gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.2, gpt-5.1, gpt-5 and gpt-5-mini accepted

After

These model IDs are no longer accepted

Action needed:
Switch direct model selections and fallback chains to a current OpenAI model such as openai/gpt-6-luna or openai/gpt-6-sol.
Full changelog, by month

Role

General-purpose model at OpenAI

  1. GPT-5.4 miniCurrent

    Mar 2026 to now · 8 months
  2. GPT-5.1 miniUntil Mar 2026
  3. GPT-5 miniAug 2025 to now · 1 year 3 months

Works with

From recorded changes
OpenAI Codex character
OpenAI Codex

Agent · 2 shared changes

Similar models

gpt-5-6-cyber

Model

GPT-5.6 Luna

$0.20 in, $1.20 out

GPT-5.6 Sol

$4 in, $20 out

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

Cost vs peers

2nd cheapest of 5 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
OpenAI$0.38 / $2.25100%
Azure$0.75 / $4.50100%

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-5.4 mini. Dark marks are similar models.

Independent

What people say

Reviews

No reviews yet. Be the first to review GPT-5.4 mini.

Used GPT-5.4 mini? Tell other builders what worked and what did not.

Writing habits

dashes used like commas, per 1,000 words
2.1
uses of "delve"
None in 36 replies
words from our AI cliché list, per 1,000 words
0.11
"not X but Y" phrases per 1,000 words
0.11
replies with headings or bullet lists
26 of 36
typical reply length in words
251 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

14.5

Overused AI words and phrases. Less slop than 50% of tracked models.

Repetition

3.2

Repeated words and ideas. Less repetition than 78% of tracked models.

Story length

10,365

Average characters per story. Longer than 88% of tracked models.