Loading...
Loading...
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 use cases such as classification, data extraction, ranking, and sub-agent execution. The model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.
Quality Index
44.4
23rd of 442
Top 5%
Coding Index
43.9
16th of 352
Top 5%
Price/1M
$0.46
381st cheapest
49% above median
Top 56%
Speed
219 tok/s
Top 5%
TTFT
2.15s
Context Window
400K
41st largest
Top 16%
Input
$0.20
per 1M tokens
Output
$1.25
per 1M tokens
Blended
$0.46
per 1M tokens
Cheaper than 44% of models. Median price is $0.31/1M tokens.
Daily
$0.46
Monthly
$13.89
219
tokens/sec
Faster than 95% of models
2.15
seconds
Faster than 13% of models
2.15
seconds
Faster than 28% of models
Market Median
46 tok/s
381% faster
Median TTFT
0.42s
413% slower
Throughput/Dollar
474
tok/s per $/1M
Speed Comparison
Context Window
400K
tokens
Larger than 84% of models
Max Output
128K
tokens
32% of context