GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.
Added Mar 17, 2026
Context Window
400.0K
Max Output
128.0K
Input Price (Auto)
$0.75/1M
Output Price (Auto)
$4.50/1M
Cache Read (Auto)
$0.075/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
23.3
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
25.3
GPQA Diamond
Graduate-level scientific reasoning
60.6%
Better than 49% of models compared
HLE
Humanity's Last Exam
5.7%
Better than 52% of models compared
IFBench
Instruction-following benchmark
38.8%
Better than 43% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
23.4%
Better than 31% of models compared
AA-LCR
Long context reasoning evaluation
30.3%
Better than 49% of models compared
SciCode
Python programming for scientific computing
39.6%
Better than 81% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
18.2%
Better than 65% of models compared
Last updated May 15, 2026
Artificial Analysis