Models / GPT-4.1 mini

OpenAI

GPT-4.1 mini

GPT-4.1 mini trails most of the field on what it has been measured on; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is gpt-oss-20b, at $0.06 per million tokens against $0.70.

Superseded. GPT-5.4 mini is OpenAI's newer model in this line, at $1.69 blended: see GPT-5.4 mini or compare the two.

Retiring 14 Jan 2027. OpenAI retires gpt-4.1-mini; the official replacement is gpt-6-luna. How to re-test before you switch.

Results 16 Nov 2026 · 33 results · 4 sources

Test GPT-4.1 mini on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.40 in · $1.60 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
10.2
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
OpenAI, based in the US
Weights not published
Released
14 Apr 2025
1,047,576 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 134th of 185Claude Opus 5.5 – $0.70 blended, 47th percentilecheapest: Mistral Nemo –
Models priced $0.25–1 per million tokens 41st of 61MiMo-V2.6-Pro – sets this group –
Models with similar intelligence sets this group – $0.70 blended, 64th percentilecheapest: gpt-oss-20b –
Models from developers based in the US 70th of 92Claude Opus 5.5 – $0.70 blended, 35th 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.

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 110th of 159 available · 28th of 47 at its price
BenchmarkGPT-4.1 miniRank among availableBest available
Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported 50.5% 14th of 36 Claude Opus 4.5 77.5%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 10.1% 90th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 5.4% 89th of 104 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • 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 141st of 187 available · 45th of 61 at its price
BenchmarkGPT-4.1 miniRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 10.2 134th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 5.0% 150th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 66.4% 125th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 118th of 169 available · 42nd of 58 at its price
BenchmarkGPT-4.1 miniRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,383 108th of 153 Gemini 4 Argon 1,525
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 131st of 139 available · 39th of 40 at its price
BenchmarkGPT-4.1 miniRank among availableBest available
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 12.7% 63rd of 68 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
  • Arena (formerly LMArena): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against GPT-4.1 mini at $0.70 blended, Intelligence Index 10.2. "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 $0.70 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Azurenot stated$0.40$1.60$0.70
OpenAInot stated$0.40$1.60$0.70
Azurenot stated$0.44$1.76$0.77

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-4.1 miniMiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
gpt-oss-20b
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.70 $0.54$0.06$8.00
Tokens a second – 4327796
Intelligence Index 10.2 46.310.057.6
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 110th of 159 23rd130th3rd
Professional work – ––3rd
Reasoning and knowledge 141st of 187 13th132nd1st
Writing 118th of 169 23rd155th5th
Sticking to the facts 131st of 139 10th–3rd
Speed under pressure – –––

Shaded figures are better than GPT-4.1 mini's. A dash means no result.

Where it has been measured

41st most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, in the bottom quarter for reasoning and knowledge, and sticking to the facts.

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

Every result

33 published results from 4 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 6 results
MeasureValueRankConfigurationDated
Arena Text: business, management and financeArena rating, higher is better 1,379
1,371–1,387
183 of 406 GPT-4.1 mini 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,349
1,340–1,358
177 of 411 GPT-4.1 mini 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,383
1,370–1,396
195 of 363 GPT-4.1 mini 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,373
1,366–1,379
183 of 413 GPT-4.1 mini 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,383
1,378–1,387
183 of 413 GPT-4.1 mini 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,361
1,354–1,368
181 of 412 GPT-4.1 mini 2 Oct 2026

Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Artificial Analysis · reported by Artificial Analysis · 10 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 20.2 157 of 187 GPT-4.1 mini 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 10.2 317 of 413 GPT-4.1 mini 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 66.4% 271 of 360 GPT-4.1 mini 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 5.0% 346 of 419 GPT-4.1 mini 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 38.3% 216 of 288 GPT-4.1 mini 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 44.0% 301 of 407 GPT-4.1 mini 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 10.1% 160 of 188 GPT-4.1 mini 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 7.6% 208 of 282 GPT-4.1 mini 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 5.4% 153 of 175 GPT-4.1 mini 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 52.9% 159 of 286 GPT-4.1 mini 20 Oct 2026

Not shown: Not your codebase or tools.

Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 16 results
MeasureValueRankConfigurationDated
BFCL: irrelevance detection% correct, higher is better 81.7% 51 of 109 GPT-4.1 mini (bfcl fc) 16 Dec 2025
BFCL: irrelevance detection% correct, higher is better 73.9% 78 of 109 GPT-4.1 mini (bfcl prompt) 16 Dec 2025
BFCL: memory% correct, higher is better 26.9% 27 of 109 GPT-4.1 mini (bfcl fc) 16 Dec 2025
BFCL: memory% correct, higher is better 24.3% 34 of 109 GPT-4.1 mini (bfcl prompt) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 34.1% 37 of 109 GPT-4.1 mini (bfcl fc) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 2.5% 91 of 109 GPT-4.1 mini (bfcl prompt) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 50.5% 27 of 109 GPT-4.1 mini (bfcl fc) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 29.7% 67 of 109 GPT-4.1 mini (bfcl prompt) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 81.3% 41 of 109 GPT-4.1 mini (bfcl fc) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 87.5% 27 of 109 GPT-4.1 mini (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 83.8% 53 of 109 GPT-4.1 mini (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 84.6% 49 of 109 GPT-4.1 mini (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 68.8% 65 of 109 GPT-4.1 mini (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 74.8% 40 of 109 GPT-4.1 mini (bfcl prompt) 16 Dec 2025
BFCL: web search% correct, higher is better 57.0% 23 of 109 GPT-4.1 mini (bfcl fc) 16 Dec 2025
BFCL: web search% correct, higher is better 4.0% 67 of 109 GPT-4.1 mini (bfcl prompt) 16 Dec 2025

Not shown: Not general refusal or safety behaviour.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 12.7% 78 of 85 GPT-4.1 mini 31 Aug 2026

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

Will GPT-4.1 mini 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.