Inference
EN
OpenAI

GPT-4o mini

GPT-4o mini is a standard model from OpenAI in the GPT-4o family. 18 benchmarks count toward its index, in 7 categories.

  • Closed weights
  • Standard
  • Input: text · image · file
  • Released 2024-07
RankedEnough results for an index.
IndexAll categories, out of 100.26.2±4.3Median 51.0
CoverageIndex weight that has results.95%
SpeedOutput tokens per second.56/sMedian 67/s
First tokenSeconds to the first output token.0.6 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.15Median $0.60
Output / 1MUS dollars per 1M output tokens.$0.60Median $2.55
ContextMaximum tokens in one request.128KMedian 262K
EloLMArena rating and rank.1286±4 #268Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
openai/gpt-4o-mini
Max outputMaximum output tokens per request.
16K
Knowledge cutoffLast date of training data.
31 Oct 2023
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.075
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
3 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
DigitalOceanCloud$0.15$0.60128K
Microsoft AzureDeprecatedCloud$0.15$0.60128K
OpenRouterRouter$0.15$0.60128K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted34.0—
CodingCode writing and repair.2 counted19.5207 / 209
ReasoningLogic problems and puzzles.3 counted41.1155 / 227
MultimodalTasks with images and text.1 counted19.0—
KnowledgeFacts and expert knowledge.5 counted25.7255 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted18.0—
MathMath problems.5 counted22.0157 / 168

Results

18 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH level 5Math52.6% ±1.146 / 88
Evaluating Large Language Models Trained on CodeCoding87.2%12 / 22
Massive Multitask Language UnderstandingKnowledge82.0%23 / 34
GDPval-AA normalizedAgentic0.0%101 / 133
Mystery Game PuzzlesReasoning12.0% ±3.361 / 80
MATH 500Math72.6% ±3.948 / 59
OTIS Mock AIME 2024-2025Math6.9% ±2.7163 / 200
GPQA diamond · Epoch AIKnowledge37.7% ±2.4179 / 217
Artificial Analysis Humanity's Last ExamKnowledge4.2%194 / 222
AIMEMath11.5% ±1.087 / 95
ARC-AGI-2 (semi-private)Reasoning0.0%120 / 131
Artificial Analysis IFBenchInstruction31.0%134 / 146
Artificial Analysis GPQA DiamondKnowledge42.6%185 / 199
GPQA Diamond · Vals AIKnowledge44.2% ±2.5127 / 135
MMMU ProMultimodal56.6% ±1.287 / 92
Artificial Analysis MMMU-ProMultimodal41.5%109 / 113
FrontierMath-Tiers-1-3-v2-PrivateMath0.7% ±0.587 / 90
MMLU ProKnowledge62.7% ±0.5131 / 135
LiveCodeBenchCoding26.4% ±1.1138 / 142
Chess PuzzlesReasoning3.0% ±1.788 / 90
SimpleQA VerifiedKnowledge8.3% ±0.990 / 91
MortgageTaxFinance54.5% ±1.979 / 97
ARC-AGI-2 (public eval)Reasoning0.0%102 / 122
MGSMMultilingual86.2% ±2.163 / 74
MedQAHealthcare72.4% ±0.881 / 95
CorpFin v2Finance45.5% ±1.0116 / 131
TaxEval v2Finance60.5% ±1.0127 / 143

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedEpoch AICC BYARC Prize FoundationTerms restrict reusemodels.devMIT

History

5 releases
Index27.1 → 26.2
23 Oct 202612 Nov 2026
Output / 1M$0.60 → $0.60
23 Oct 202612 Nov 2026

Questions

How much does GPT-4o mini cost?
$0.15 per 1M input tokens, $0.60 per 1M output tokens.
How good is GPT-4o mini?
Its index is 26.2 out of 100. That is place 266 of 283 ranked models.
What is GPT-4o mini best at?
Reasoning: 41.1 out of 100, place 155 of 227.
How fast is GPT-4o mini?
56 output tokens per second, 0.6 s to the first token.
What is the context window of GPT-4o mini?
128K tokens.
Is GPT-4o mini open source?
No. Its weights are not published.
When was GPT-4o mini released?
July 2024.

Badge

GPT-4o mini on Inference360: place 266 of 283, index 26.2
HTML
<a href="https://inference360.ai/models/gpt-4o-mini"><img src="https://inference360.ai/badges/gpt-4o-mini.svg" alt="GPT-4o mini on Inference360: place 266 of 283, index 26.2" height="20"></a>
Markdown
[![GPT-4o mini on Inference360: place 266 of 283, index 26.2](https://inference360.ai/badges/gpt-4o-mini.svg)](https://inference360.ai/models/gpt-4o-mini)

Compare with

GPT-4.1 nano26.3Llama 4 Scout26.8Nova Pro25.6Gemma 3 27B25.3GPT-4o28.7

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from OpenAI

All models
o1-mini33.5o1-previewUnrankedGPT-4o28.7GPT-4o AudioUnrankedo144.5