ChatGPT
ChatGPT

GPT-5.4 Mini

Model ID:gpt-5.4-mini-2026-03-17
2026-03-17Proprietary Model
API
OverallNo.21
PopularityNo.21

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, and tool use, while reducing latency and cost for large-scale deployments. The model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.

Knowledge Cutoff
2025-08-31

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory
400KIN128KOUT

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words
$0.75IN$4.5OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

AI Performance Evaluation

Arena Overall Score
1457
±9
As of 2026-04-02
Overall Rank
No.21
5,019 Votes
Arena by Ability
Hard Prompts
1484±11No.19
Expert Knowledge
1493±30No.15
Instruction Following
1450±15No.20
Conversation Memory
1482±19No.12
Creative
1413±22No.37
Coding
1512±17No.17
Math
1412±33No.72
Arena by Occupation
Creative Writing
1429±17No.31
Social Sciences
1477±21No.20
Media
1420±20No.32
Business
1479±19No.8
Healthcare
1475±34No.29
Legal
1471±31No.18
Software
1495±14No.21
Mathematics
1459±37No.24
Reasoning Ability
AA Intelligence Index
38%↓1%
GPQA Diamond
82%↑0%
HLE
17%↑0%
Coding Ability
AA Coding Index
38%↑1%
SciCode
44%↑2%
TerminalBench
34%↑0%
Instruction Following
IFBench
65%↑8%
Long Context
AA-LCR
61%↓2%
Agentic AI Ability
TAU2
37%↓35%
Speed
Standard Mode
172tok/sec↑94
First Output 0.48s
Artificial Analysis
Reasoning Mode
181tok/sec↑109
First Output 5.40s
Artificial Analysis