GPT 5.4 Low
OpenAI logo

GPT 5.4 Low

gpt-5.4-low
OpenAI
GPT-5.4 supports configuring reasoning strength only through the /responses endpoint. To make lower-overhead reasoning available directly in the /chat endpoint, the GPT-5.4-Low model is provided. This model is based on GPT-5.4 with reasoning_effort preset to low. This model is designed for use cases that are sensitive to response latency and cost. By adopting a lighter reasoning strategy, it delivers stable responses with lower latency and higher throughput. It is well suited for high-concurrency conversations, real-time interactions, basic Q&A, and scenarios where deep reasoning is not required.

Pricing

TierPricingCache ReadImage GenerationWeb Search
Input<=272K
$2.500$15.000
$0.25/M tokens-$0.01/request
272K<Input
$5.000$22.500
$0.5/M tokens-$0.01/request

Input Modalities

  • Text
  • Vision

Output Modalities

  • Text

Capabilities

  • Thinking
  • Web
  • Tools
  • Tool calling
  • Structured outputs

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="gpt-5.4-low",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is GPT 5.4 Low?

GPT-5.4 supports configuring reasoning strength only through the /responses endpoint. To make lower-overhead reasoning available directly in the /chat endpoint, the GPT-5.4-Low model is provided. This model is based on GPT-5.4 with reasoning_effort preset to low. This model is designed for use cases that are sensitive to response latency and cost. By adopting a lighter reasoning strategy, it delivers stable responses with lower latency and higher throughput. It is well suited for high-concurrency conversations, real-time interactions, basic Q&A, and scenarios where deep reasoning is not required.