About
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. It supports text and image inputs and is designed for low-latency...
Related Models
Pricing
Input
$0.20
per 1M tokens
Output
$1.25
per 1M tokens
Blended
$0.46
per 1M tokens
Cheaper than 53% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.46
Monthly
$13.88
vs. Similar Models
MiniMax: MiniMax M2.7Q:-0.1
$0.32-32%
MoonshotAI: Kimi K2.5Q:-0.1
$0.79+70%
Z.ai: GLM 5 TurboQ:-0.1
$1.90+311%
GPT-5.2 (medium)Q:-0.2
$4.81+941%
Performance
162
tokens/sec
Faster than 78% of models
2.87
seconds
Faster than 20% of models
2.87
seconds
Faster than 50% of models
Market Median
94 tok/s
72% faster
Median TTFT
1.11s
158% slower
Throughput/Dollar
350
tok/s per $/1M
Speed Comparison
Nova 2.0 Pro Preview (Non-reasoning)
162 tok/s-0%
Gemini 3 Pro Preview (high)
161 tok/s-0%
GPT-5.4 mini (Non-Reasoning)
162 tok/s+0%
Context Window
400K
tokens
Larger than 76% of models
Max Output
128K
tokens
32% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
81.7%
HLE
26.5%
LiveCodeBenchNot evaluated
SciCode
46.9%
TerminalBench Hard
42.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
75.9%
Long Context Recall
66.0%
Tau2
76.0%
Market AverageTop Score