GPT-5.4 Nano by ZenMux — Specs, Pricing & Capabilities | whichllm

Model ID openai/gpt-5.4-nano

Provider ZenMux

Family -

Status -

Knowledge Cutoff 2025-08-31

Release Date 2026-03-20

Input Modalities text

Output Modalities text

Context Window 400000

Input Limit -

Output Limit 128000

Tool Calling Yes

Reasoning No

Structured Output -

Temperature Control Yes

Open Weights No

Input Cost / 1M tokens $0.20

Output Cost / 1M tokens $1.25

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens -

Cache Write Cost / 1M tokens -