OpenAI: GPT-5.4 Nano

Text input File input Image input Text output
Author's Description

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 use cases such as classification, data extraction, ranking, and sub-agent execution. The model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.

Key Specifications
Cost
$$
Context
400K
Released
Mar 17, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Seed Max Tokens Structured Outputs Tool Choice Response Format Reasoning Include Reasoning
Features

This model supports the following features:

Tools Structured Outputs Response Format Reasoning
Performance Summary

OpenAI's GPT-5.4 Nano, released on March 17, 2026, is a highly optimized, lightweight model designed for speed-critical and high-volume tasks. It consistently ranks among the fastest models, achieving the 94th percentile across 8 benchmarks, and offers competitive pricing, typically falling within the 68th percentile. A standout feature is its exceptional reliability, demonstrating a 100% success rate across all benchmarks, indicating minimal technical failures. In terms of performance across categories, GPT-5.4 Nano excels in areas requiring rapid, reliable outputs. It shows strong performance in Hallucinations (96.0% accuracy) and Email Classification (96.0% accuracy), aligning with its design for classification and data extraction. Its Mathematics performance is notable, achieving 74.0% accuracy and ranking in the top 3 for speed. However, its accuracy in Reasoning (44.0%) and Coding (79.0%) is comparatively lower, suggesting it prioritizes responsiveness and efficiency over deep, complex problem-solving. General Knowledge (95.0%) and Ethics (97.0%) also show solid accuracy but with lower percentile rankings, indicating a focus on breadth rather than specialized depth.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.2
Completion $1.25
Input Cache Read $0.02
Web Search $10000

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/gpt-5.4-nano-20260317 400K $0.2 / 1M tokens $1.25 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai