Skip to content

OpenAI · Chat

GPT 5.4 Nano

OpenAI 🇺🇸ChatGPT familyOne of its sources says the weights aren't publicly available.The maker currently plans to deprecate it within the next 180 days (1 Apr 2027). Plans can change.
From Neosantara's listing:
GPT 5.4 Nano is the smallest and most affordable model in the GPT-5.4 family for high-volume sub-agent workflows.
llminfo IQ
120.3
Max context
410K
Listings
58

Evidence and sources

llminfo IQ 120.3, ranked among chat models. From 252 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 103.6, 95% interval 97–110. From 13 benchmark families across 7 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 computedFair value (49.5). Costs per task about what its benchmark results predict. From 32 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 (47 ±9). 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.Median 21,398 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: #83 on OpenRouter today #95 on OpenRouter this week #108 on OpenRouter this month #301 on NanoGPT recentlySources: OpenAI API data, Writer Pricing, LiteLLM data, Models.dev data, AI/ML API data, OpenRouter data docs, Neosantara Inference data, llminfo researchPrimary data from OpenAI API from Writer Pricing: 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

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 1 Apr 2027, within the next 180 days.

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, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices; 3 market median prices.

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-nanoSources: GenAI Prices data, LiteLLM data, Models.dev data, OpenAI API data272K$0.20cache read $0.02batch $0.10$1.25batch $0.625——
 OpenRouterInference by OpenAIopenai/gpt-5.4-nano · flexSource: OpenRouter data docs400K$0.10cache read $0.01$0.62568985ms
 Vercelopenai/gpt-5.4-nano-batch · batchSource: Vercel AI Gateway data400K$0.10cache read $0.01$0.625——
 Neosantaragpt-5.4-nanoSource: Neosantara Inference data400K——
 Poeopenai/gpt-5.4-nanoSource: Models.dev data400K$0.1818cache read $0.0182$1.1364——
 Tokenmixgpt-5.4-nanoSources: TokenMix data, TokenMix PricingNot published by the provider$0.194$1.2125——
 Databricksdatabricks/databricks-gpt-5-4-nanoSources: LiteLLM data, Models.dev data272K$0.20cache read $0.02$1.25cache write $0.20——
 Microsoft AzureRegions: 🇦🇺🇧🇷+17 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, 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-nanoSources: Azure OpenAI, LiteLLM data, Models.dev data272K$0.20cache read $0.02batch $0.10$1.25batch $0.625——
 302aigpt-5.4-nanoSources: 302.ai data, Models.dev data400K$0.20cache read $0.02$1.25——
 Aihubmixgpt-5.4-nanoSources: AIHubMix data docs, LiteLLM data400K$0.20cache read $0.02$1.25——

7 listings without a price are hidden.

Benchmarks

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

Human preference

Arena ELO60 related benchmarks · 60 results
Source: LMArena data · Nov 2026
BenchmarkHigh
Arena ELO
Chinese
Creative Writing
English
Show 56 more benchmarksHide 56 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 - German
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 - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
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

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 64.2% median 64.9% highest 65.6%OpenRouter's automatic routing 64.7%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • OpenAI
  • OpenRouter's automatic routing
  • Azure

Coding

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 77.4% median 77.5% highest 77.6%OpenRouter's automatic routing 77.7%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • OpenRouter's automatic routing
  • OpenAI
  • Azure

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

Multilingual

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-nano-2026-03-17: xhigh-effort
4 subset: haerae_bench_v1_rc
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: haerae_bench_v1_wo_rc
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: hrm8k
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: kmmlu
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: kmmlu_pro
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-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-nano-2026-03-17: xhigh-effort
4 subset: ko_arc_agi
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: ko_balt_700_semantic
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: ko_balt_700_syntax
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: ko_hallulens_nonexistent
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: ko_hallulens_wikiqa
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: ko_hle
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: ko_moral
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: ko_truthful_qa
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: kobbq
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: korean_hate_speech
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4 subset: squad_kor_v1
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: ALT_유해성방지
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: ALT_윤리/도덕
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: ALT_제어성
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: ALT_편향성방지
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: FINAL_SCORE
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_구문해석
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_논리적추론
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_수학적추론
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_의미해석
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_일반적지식
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_전문적지식
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_정보검색
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_추상적추론
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_코딩능력
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_표현
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: GLP_함수호출
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: 가치정렬성능(ALT)_AVG
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-effort
4: 범용언어성능(GLP)_AVG
Source: Horangi Korean Leaderboard 4 data docs
gpt-5.4-nano-2026-03-17: xhigh-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.
Vals10 related benchmarks · 12 results
EMB
Source: Vals AI
CaseLaw v2
Source: Vals AI
CorpFin v2
Source: Vals AI
LegalBench
Source: Vals AI
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
Show 5 more resultsHide 5 results
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MortgageTax
Source: 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) · 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 · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Around the web

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

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