GPT-5.4 Mini
JSON →A smaller, efficient variant of GPT-5.4 optimized for low-latency tasks with reduced computational cost.
Specs
context window 272K tokens
max output 128K tokens
input price $0.75 / 1M tokens
output price $4.5 / 1M tokens
Capabilities
streamingcode-generationfunction-callingjson-modetool-usevisionprompt-cachingreasoning
Dates
releasedMar 2026
knowledge cutoffDec 2025
Resources
API
full doc /v1/models/gpt-5.4-mini-2026-03-17