GPT-5.4 Nano

OpenAI chatreasoningtool_usevision Long

API ID: openai/gpt-5.4-nano-20260317

Input Price
$0.20
/1M tokens
Output Price
$1.25
/1M tokens
Cached Input
$0.02
Save 90%

About GPT-5.4 Nano

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

๐Ÿ’ฐ
Price Ranking
#886 lowest price among 1240 Chat models

Model Specifications

Context Length
400k
Max Output
128k
Release Date
2026-03-17
Capabilities
chat reasoning tool_use vision
Input Modalities
fileimagetext
Output Modalities
text

Best For

  • Complex reasoning, math problems, multi-step logic
  • Image analysis, document understanding, visual Q&A
  • Conversations, content writing, general assistance

Consider Alternatives For

  • Simple Q&A (cheaper models available)

๐Ÿ’ฐ Real-World Cost Examples

Estimated monthly costs for common use cases

Personal AI Assistant
$0.47
/month
50 conversations/day, ~500 tokens each
Customer Service Bot
$14.25
/month
1000 tickets/day, ~800 tokens each
Data Analysis Pipeline
$19.50
/month
500 analyses/day, ~2k tokens each

OpenAI Model Lineup

Compare all models from OpenAI to find the best fit

Model Input Output Context Capabilities
GPT-5.4 Nano Current Free Free 400k chat reasoning tool_use vision
GPT-3.5 Turbo 16k (older v1106) Free Free 16k chat
GPT-3.5 Turbo 16k (older v1106) Free Free 16k chat
GPT-4 32k Free Free 33k chat
GPT-4 32k Free Free 33k chat
GPT-4 32k (older v0314) Free Free 33k chat

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Meta Llama 3.3 70B Instruct
Input: $0.72
Output: $0.72
Context: 131k
Meta Llama 3.1 70B Instruct
Input: $0.72
Output: $0.72
Context: 131k
Moonshot AI Kimi Dev 72B
Input: $0.29
Output: $1.15
Context: 131k
Alibaba Qwen Qwen3 VL 8B Thinking
Input: $0.12
Output: $1.36
Context: 131k

๐Ÿš€ Quick Start

Get started with GPT-5.4 Nano API

OpenAI Python SDK
from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
    model="openai/gpt-5.4-nano-20260317",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)