Skip to main content

GPT-5.4 Mini

Approved Data Classifications

Description

GPT-5.4 Mini is OpenAI’s high-throughput small model designed for fast, cost-efficient coding, reasoning, and multimodal workloads. It supports text and image input, produces text output, and keeps the GPT-5.4 family’s 400,000-token context window while lowering cost and latency for production applications. OpenAI positions it as a strong default for high-volume agentic and developer workflows, with pricing at $0.75 per 1M input tokens, $4.50 per 1M output tokens, and $0.075 per 1M cached input tokens.

Capabilities

ModelKnowledge CutoffInputOutputContext LengthCost (per 1 million tokens)
gpt-5.4-miniAug 31 2025Text, ImageText400,000$0.75/1M input
$4.50/1M output
info
  • 1M represents 1 Million Tokens
  • All prices listed are based on 1 Million Tokens
  • Cached input: $0.075 per 1M tokens

Availability

Cloud Provider

Usage

curl -X POST https://api.ai.it.ufl.edu/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
"model": "gpt-5.4-mini",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Write a haiku about an Alligator."
}
]
}'

References

  1. OpenAI - Introducing GPT-5.4 mini and nano
    https://openai.com/index/introducing-gpt-5-4-mini-and-nano/
  2. OpenAI API Docs - GPT-5.4 mini
    https://developers.openai.com/api/docs/models/gpt-5.4-mini
  3. OpenAI API Pricing
    https://developers.openai.com/api/docs/pricing