GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.
Added Mar 17, 2026
Context Window
400.0K
Max Output
128.0K
Input Price (Auto)
$0.20/1M
Output Price (Auto)
$1.25/1M
Cache Read (Auto)
$0.020/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
24.4
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
27.9
GPQA Diamond
Graduate-level scientific reasoning
55.8%
Better than 41% of models compared
HLE
Humanity's Last Exam
4.2%
Better than 20% of models compared
IFBench
Instruction-following benchmark
32.7%
Better than 25% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
34.8%
Better than 50% of models compared
AA-LCR
Long context reasoning evaluation
24.7%
Better than 44% of models compared
SciCode
Python programming for scientific computing
35.2%
Better than 65% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
24.2%
Better than 72% of models compared
Last updated May 15, 2026
Artificial Analysis
