Inferbase
Beta
GPT-5.4-NANO
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.
Input
Output
Context
400K
Max Output
128K
Parameters
—
Technical Specifications
Model TypeChat
Context Window400K
Max Output Tokens128K
Parameters—
Training Cutoff—
License—
Capabilities
Input Modalities
fileimagetext
Output Modalities
text
Pricing
per 1M tokens • updated regularlyPricing
Input
$0.200
Output
$1.25
Available on 1 Platform
| Platform | Input | Output |
|---|---|---|
OpenRouter | $0.200 | $1.25 |
Benchmarks
14.7%
HLE
76.1%
GPQA
38.4%
SciCode
35.0
Coding
38.1
Intelligence
219
Speed (tok/s)
4.1
TTFA (s)
4.1
TTFT (s)
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Mar 31, 2026
Build Your AI Stack with Confidence
Compare pricing, benchmarks, and GPU requirements for any model. Free to use.