Skip to content

OpenAI · Chat

GPT-5.4 mini

OpenAI 🇺🇸ChatGPT familyOne of its sources says the weights aren't publicly available.The maker currently lists 21 Sep 2027 as the deprecation date. Plans can change.
From Neosantara's listing:
GPT-5.4 Mini model with agentic reasoning and fast responses
llminfo IQ
128.1
Max context
410K
Listings
72

Evidence and sources

llminfo IQ 128.1, ranked among chat models. From 307 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 104.3, 95% interval 99–110. From 18 benchmark families across 12 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (39.8). Costs more per task than its benchmark results predict. From 33 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTypical (46 ±18). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. By effort: default 46 · low 43 · medium 54 · high 58 · max 56.Median 30,620 output tokens per task at default effort.How the Yap score worksReleased 17 Mar 2026 Training-data cutoff, as its sources state it Maker HQ: US (according to OpenAI's own website)
All rankings: #105 on OpenRouter this month #108 on OpenRouter today #111 on OpenRouter this week #225 on NanoGPT recentlySources: OpenAI API data, LMArena data, LiteLLM data, Models.dev data, AI/ML API data, OpenRouter data docs, Neosantara Inference data, llminfo researchPrimary data from OpenAI API from LMArena: name, variant from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode from OpenRouter: knowledge cutoff from Neosantara Inference: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Images
Files
Text
Images

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputWeb searchBatch API

Listings

 OpenAIgpt-5.4-miniSources: GenAI Prices data, LiteLLM data, Models.dev data, OpenAI API data272K$0.75cache read $0.075batch $0.375$4.50batch $2.25———
 OpenRouterInference by OpenAIopenai/gpt-5.4-mini · flexSource: OpenRouter data docs400K$0.375cache read $0.0375$2.25—90597.5ms
 Vercelopenai/gpt-5.4-mini-batch · batchSource: Vercel AI Gateway data400K$0.375cache read $0.0375$2.25———
 Xpersonagpt-5.4-miniSources: Models.dev data, Xpersona data272K$0.375cache read $0.0375$4.00$0.001——
 Poeopenai/gpt-5.4-miniSource: Models.dev data400K$0.6818cache read $0.0682$4.0909———
 Tokenmixgpt-5.4-miniSources: TokenMix data, TokenMix PricingNot published by the provider$0.7275$4.365———
 Databricksdatabricks/databricks-gpt-5-4-miniSources: LiteLLM data, Models.dev data272K$0.75cache read $0.075$4.50cache write $0.75———
 Microsoft AzureRegions: 🇦🇺🇧🇷+18 australia-east, brazil-south, canada-east, us-central, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, qatar-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3gpt-5.4-miniSources: Azure OpenAI, LiteLLM data, Models.dev data272K$0.75cache read $0.075batch $0.375$4.50batch $2.25———
 302aigpt-5.4-miniSources: 302.ai data, Models.dev data400K$0.75cache read $0.075$4.50———
 Aihubmixgpt-5.4-miniSources: AIHubMix data docs, LiteLLM data400K$0.75cache read $0.075$4.50———

10 listings without a price are hidden.

Included in plans

Copilot EnterprisegithubSubscription$39/moextra use billed past the allowancePlan page
Copilot ProgithubSubscription$10/moextra use billed past the allowancePlan page
Copilot Pro+githubSubscription$39/moextra use billed past the allowancePlan page
Copilot BusinessgithubSubscription$19/moextra use billed past the allowancePlan page
Copilot MaxgithubSubscription$100/moextra use billed past the allowancePlan page

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO61 related benchmarks · 61 results
Source: LMArena data · Nov 2026
BenchmarkHigh
Arena ELO
Chinese
Creative Writing
English
Show 57 more benchmarksHide 57 benchmarks
BenchmarkHigh
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Japanese
Text Factuality - Korean
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Entity Recognition
Vision - Homework
Vision - Humor
Vision Style-Controlled

Long context

GDM-MRCRv2: 8 needle7 related benchmarks · 35 results
Source: Context Arena data · Apr 2026
Benchmarklowmediumhighxhighnot stated
GDM-MRCRv2: 8 needle
8k
16k
32k
Show 3 more benchmarksHide 3 benchmarks
Benchmarklowmediumhighxhighnot stated
64k
128k
256k

Reasoning

Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
xhigh · without tools
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Agentic

GAIA4 results
Source: GAIA Leaderboard data · Aug 2026
Difficulty level
Difficulty not reported
MCP Atlas2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
xhigh · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
xhigh · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-Bench Pro2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Source: OpenRouter benchmark exports · Oct 2026
17 Mar 2026 version · 90-day results
Across 2 providers lowest 64.9% median 65.9% highest 66.8%OpenRouter's automatic routing 66.7%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • Azure
  • OpenRouter's automatic routing
  • OpenAI
TBench2 results
Source: Terminal-Bench · Mar 2026
terminal-bench-4.0, Codex
terminal-bench-4.1, Codex

Coding

Arena ELOSource: LMArena data · Nov 2026
ValsSource: Vals AI

Math

General

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond7 results
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
xhigh · published setting
Source: OpenRouter benchmark exports · Oct 2026
17 Mar 2026 version · 90-day results
Across 2 providers lowest 83.8% median 84% highest 84.2%OpenRouter's automatic routing 83.8%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • OpenAI
  • Azure
  • OpenRouter's automatic routing

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs

Vision

MMMU-Pro3 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
xhigh
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Factuality

Instruction following

Knowledge

OCR

Other

ArmBench-LLM Armenian22 related benchmarks · 22 results
GraphWalks BFSReported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GraphWalks Parentsxhigh · 0K–128K · accuracy · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Horangi36 related benchmarks · 36 results
4: ALT_환각방지
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: haerae_bench_v1_rc
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: haerae_bench_v1_wo_rc
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: hrm8k
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: kmmlu
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: kmmlu_pro
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
Show 30 more resultsHide 30 results
4 subset: ko_aime2025
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: ko_arc_agi
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: ko_balt_700_semantic
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: ko_balt_700_syntax
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: ko_hallulens_nonexistent
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: ko_hallulens_wikiqa
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: ko_hle
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: ko_moral
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: ko_truthful_qa
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: kobbq
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: korean_hate_speech
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4 subset: squad_kor_v1
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: ALT_유해성방지
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: ALT_윤리/도덕
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: ALT_제어성
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: ALT_편향성방지
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: FINAL_SCORE
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_구문해석
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_논리적추론
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_수학적추론
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_의미해석
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_일반적지식
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_전문적지식
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_정보검색
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_추상적추론
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_코딩능력
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_표현
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: GLP_함수호출
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: 가치정렬성능(ALT)_AVG
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
4: 범용언어성능(GLP)_AVG
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-mini-2026-03-17: xhigh-effort
Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_表現
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.4-mini-2026-03-17: high-effort
OmniDocBench · NEDxhigh · OmniDocBench 1.5 · no tools · reasoning_effort none · overall edit distance · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ValsSource: Vals AI

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · ArmBench-LLM by Metric-AI. Public numeric primary task results; no separate results licence asserted. · BullshitBench by Peter Gostev, MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Terminal-Bench (Laude Institute), Apache-2.0 (licence) · Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Around the web

Also known as: aihubmix/gpt-5.4-mini, azure/eu/gpt-5.4-mini, azure/gpt-5.4-mini, azure/gpt-5.4-mini-2026-03-17, azure/gpt-5.4-mini@eastus2, azure/us/gpt-5.4-mini, azure_ai/gpt-5.4-mini, azure_ai/gpt-5.4-mini-2026-03-17, databricks-gpt-5-4-mini, databricks/databricks-gpt-5-4-mini, github_copilot/gpt-5.4-mini, gmi/openai/gpt-5.4-mini, gpt-5-4-mini, gpt-5.4 mini, gpt-5.4-mini-2026-03-17, gpt-5.4-mini-high, gpt-54-mini, openai-gpt-5.4-mini, openai-gpt-54-mini, openai/gpt-5.4-mini, openai/gpt-5.4-mini-batch, openai/gpt-5.4-mini-fast, openai/gpt-5.4-mini:batch, perplexity/openai/gpt-5.4-mini

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works