GPT 5.4 Mini

"vendor": "openai""model_name": "gpt-5.4-mini"

OpenAI GPT-5.4 Mini - a fast and cost-effective model for lightweight tasks with cached input support

LLMNew

VENDOROpenAI

INPUTtitleimage

OUTPUTtitle

PRICING

Hover to view▾

gpt-5.4-mini

AI can make mistakes. Verify important information.

README for GPT 5.4 Mini

GPT-5.4 Mini is a fast and cost-effective model in the GPT-5.4 family, ideal for lightweight tasks that need quick responses at lower cost.

OpenAI-compatible API - Use /vendors/openai/v1/chat/completions or /vendors/openai/v1/responses
Cached input support - Further cost savings on repeated prompts
Streaming support - Real-time token streaming

Endpoint	Path
Chat Completions	`/vendors/openai/v1/chat/completions`
Responses	`/vendors/openai/v1/responses`

Set model to gpt-5.4-mini in your request body.

Per Million Tokens

Input: $0.75
Cached Input: $0.075
Output: $4.50