GPT-5.4 mini
OpenAI · 3 thinking configurations
Intelligence24.1
Input / 1M$0.75
Output / 1M$4.50
Context400K
Tariff: OpenAI · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 2 without both values
Selected: thinking xhigh · Click a point to switch configuration
GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
24.1 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
87.5 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
28.1 %SciCodeCode generation for scientific research problems.
52.1 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
59.2 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
83.3 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
73.3 %MMMU-ProMultimodal understanding of academic problems that include images.
73.3 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
37.5 %Specifications from the catalog
Inputfile, image, text
Outputtext
Tool callingYes
Structured outputYes
Speed224.4 tok/s
First token128.04 s
Maximum output128K
Catalog listing date2026-03-17