Models / GPT-5.4 nano

OpenAI

GPT-5.4 nano

GPT-5.4 nano is strongest at agents and tool use; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is Gemma 4 26B A4B, at $0.14 per million tokens against $0.46.

Retiring 1 Apr 2027. OpenAI retires gpt-5.4-nano; the official replacement is gpt-6-luna. How to re-test before you switch.

Results 16 Nov 2026 · 46 results · 5 sources

Test GPT-5.4 nano on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.20 in · $1.25 out
OpenAI's list price, 10 Nov 2026 · compare prices$0.02 cached input
Speed
Not measured
Intelligence Index
20.7
Artificial Analysis, at xhigh reasoning; 11.7–20.7 across 3 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
OpenAI, based in the US
Weights not published
Released
17 Mar 2026
400,000 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 96th of 185Claude Opus 5.5 – $0.46 blended, 36th percentilecheapest: Mistral Nemo –
Models priced $0.25–1 per million tokens 22nd of 61MiMo-V2.6-Pro – sets this group –
Models with similar intelligence sets this group – $0.46 blended, 20th percentilecheapest: Gemma 4 26B A4B –
Models from developers based in the US 53rd of 92Claude Opus 5.5 – $0.46 blended, 26th percentilecheapest: Gemma 3 4B –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

Measured cost per task

API cost recorded in our benchmark runs, excluding judging.

TaskBenchmarkCost per task
Game of bullet chessBulletBench≈ $0.005

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $0.25–1 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 74th of 159 available · 11th of 47 at its price
BenchmarkGPT-5.4 nanoRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.5% 62nd of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 60.7% 47th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 27.4% 36th of 104 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 96th of 187 available · 22nd of 61 at its price
BenchmarkGPT-5.4 nanoRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 20.7 96th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 28.3% 82nd of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 81.7% 87th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 103rd of 169 available · 31st of 58 at its price
BenchmarkGPT-5.4 nanoRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,401 96th of 153 Gemini 4 Argon 1,525
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 82nd of 139 available · 17th of 40 at its price
BenchmarkGPT-5.4 nanoRank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 3.1% 1st of 71 This model
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,418 86th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 11.7% 64th of 68 GPT-6 Astra 75.6%
Speed under pressureGood decisions against a real clock (fast chess) 30th of 35 available · 7th of 8 at its price
BenchmarkGPT-5.4 nanoRank among availableBest available
BulletBenchBulletBench Lightning 10+1: ladder Elo 197 14th of 18 Gemini 3.5 Flash-Lite 892
BulletBenchBulletBench Bullet 60s: ladder Elo 33 30th of 33 Gemini 3.8 Flash 1,068

Nearest alternatives

Against GPT-5.4 nano at $0.46 blended, Intelligence Index 20.7. "Similar intelligence" means within 4 points or better.

Where to run it

3 hosts on OpenRouter at the standard service tier, with a median of $0.46 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Azurenot stated$0.20$1.25$0.46
OpenAInot stated$0.20$1.25$0.46
Azurenot stated$0.22$1.38$0.51

Other service tiers, not counted above: OpenAI flex $0.10 in, $0.62 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

GPT-5.4 nanoMiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
Gemma 4 26B A4B
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.46 $0.54$0.14$8.00
Tokens a second – 438296
Intelligence Index 20.7 46.316.757.6
Spring Prompt overall – ––82
Rank among available models, by use case
Product listings – ––13th
Decks from an analysis – ––7th
User surveys – ––4th
Marketing planning – ––9th
Agents and tool use 74th of 159 23rd105th3rd
Professional work – ––3rd
Reasoning and knowledge 96th of 187 13th110th1st
Writing 103rd of 169 23rd82nd5th
Sticking to the facts 82nd of 139 10th43rd3rd
Speed under pressure 30th of 35 –––

Shaded figures are better than GPT-5.4 nano's. A dash means no result.

Where it has been measured

22nd most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, in the bottom quarter for speed under pressure.

Artificial Analysis lists it but has not published a speed for it yet

Every result

46 published results from 5 sources, each in the source's own units, with the configuration that produced it.

BulletBench · measured by Spring Prompt · 10 results
MeasureValueRankConfigurationDated
BulletBench Bullet 60s: cost per gameUS dollars, lower is better $0.0050 35 of 71 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: games lost on time% of games, lower is better 66.7% 53 of 71 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: invalid moves% of moves, lower is better 3.1% 70 of 71 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: ladder Eloladder Elo, higher is better 33
0–273
66 of 71 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026
BulletBench Bullet 60s: median move timemilliseconds, lower is better 1.1 s 34 of 71 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: cost per gameUS dollars, lower is better $0.0025 26 of 48 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: games lost on time% of games, lower is better 75.0% 42 of 48 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: invalid moves% of moves, lower is better 4.0% 47 of 48 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: ladder Eloladder Elo, higher is better 197
0–425
41 of 48 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026
BulletBench Lightning 10+1: median move timemilliseconds, lower is better 1.0 s 37 of 48 GPT-5.4 nano (no reasoning)
none reasoning
1 Oct 2026

Not shown: Not your cost: prices are those charged on the run date.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
MeasureValueRankConfigurationDated
Arena Text factuality: overallArena rating, higher is better 1,418
1,415–1,421
135 of 182 GPT-5.4 nano (high reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,405
1,399–1,412
151 of 406 GPT-5.4 nano (high reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,336
1,329–1,344
194 of 411 GPT-5.4 nano (high reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,437
1,429–1,446
134 of 363 GPT-5.4 nano (high reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,387
1,381–1,392
161 of 413 GPT-5.4 nano (high reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,401
1,398–1,405
158 of 413 GPT-5.4 nano (high reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,363
1,357–1,369
179 of 412 GPT-5.4 nano (high reasoning) 2 Oct 2026

Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Artificial Analysis · reported by Artificial Analysis · 26 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 56.1 85 of 187 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 20.0 212 of 413 GPT-5.4 nano (medium reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 11.7 297 of 413 GPT-5.4 nano (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 20.7 203 of 413 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 76.1% 211 of 360 GPT-5.4 nano (medium reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 55.8% 308 of 360 GPT-5.4 nano (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 81.7% 162 of 360 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 15.9% 224 of 419 GPT-5.4 nano (medium reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 4.1% 380 of 419 GPT-5.4 nano (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 28.3% 159 of 419 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 64.4% 91 of 288 GPT-5.4 nano (medium reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 32.7% 251 of 288 GPT-5.4 nano (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 75.9% 21 of 288 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 67.3% 219 of 407 GPT-5.4 nano (medium reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 29.7% 342 of 407 GPT-5.4 nano (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 76.7% 137 of 407 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 47.2% 134 of 205 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 60.7% 90 of 188 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.5% 143 of 204 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 33.3% 88 of 282 GPT-5.4 nano (medium reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 24.2% 132 of 282 GPT-5.4 nano (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 42.4% 45 of 282 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 27.4% 70 of 175 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 52.6% 160 of 286 GPT-5.4 nano (medium reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 34.8% 192 of 286 GPT-5.4 nano (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 76.0% 109 of 286 GPT-5.4 nano (xhigh reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 11.7% 81 of 85 GPT-5.4 nano (high reasoning) 27 Aug 2026

Not shown: Not answers grounded in your documents; tests what the model remembers.

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 100.0% 1 of 108 GPT-5.4 nano 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 3.1% 2 of 108 GPT-5.4 nano 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Embed a score badge

A badge for each of our benchmarks that ranked GPT-5.4 nano, from the current results. Paste the code into a page or README; it links back to the benchmark.

GPT-5.4 nano is #40 of 45 on BulletBench (Lightning 10+1: 197), measured by Spring Prompt BulletBench · Lightning 10+1
<a href="https://springprompt.com/benchmarks/bulletbench?focus=openai-gpt-5-4-nano"><img src="https://springprompt.com/badge/bulletbench/openai-gpt-5-4-nano.svg" alt="GPT-5.4 nano is #40 of 45 on BulletBench (Lightning 10+1: 197), measured by Spring Prompt" height="20"></a>

Will GPT-5.4 nano work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.