Skip to contentGPT-5.4 nano
CurrentVerified ·
Smallest, lowest-cost GPT-5.4 variant for latency- and cost-sensitive workloads, with a 400K context window.
profile normalized against the 88-model field
Context window· 400K of 10M4%
Max output· 128K of 384K33%
Affordability· $1.25 / Mtok out99%
Capability breadth· 2 of 1118%
Capability switches · 2 of 11
Reasoning mode
Tool / function use
Streaming
JSON mode
Structured outputs
Prompt caching
Fine-tuning
Web search
Code execution
Vision input
Audio input
Specifications
Every value carries a primary source and a verification date.
Pricing
Input $/Mtok$0.20 / Mtok
Cached input $/Mtok$0.02 / Mtok USD/Mtok
Output $/Mtok$1.25 / Mtok
Capabilities
Tool / function useYes
API
API model IDgpt-5.4-nano
General
Knowledge cutoffAugust 31, 2025