whichllmmodel
Back to Dashboard
💬 Text ModelProprietary

GPT-5.4 nano

by OpenAI

✍️ Analysis by:the whichllmmodel Editorial Team|📅 Updated: June 2026
API Reference

Benchmark Evaluations

Codingswe-bench-pro

52.4%

Reasoninggpqa-diamond

81.7%

Pricing & Speed Details

Input Cost

$0.20

per 1M tokens
Output Cost

$1.25

per 1M tokens
Blended Cost

$0.46

based on 3:1 ratio
Speed

191 tps

Context Window

400k tokens

Want to test this model?

Compare GPT-5.4 nano dynamically against other top AI models on our comparison dashboard to optimize your choice.

Go to Dashboard

Quick Info

  • ProviderOpenAI
  • CategoryText / Chat Generation
  • LicenseProprietary

Frequently Asked Questions

GPT-5.4 nano has a blended cost of $0.46 per 1 million tokens (calculated using a standard 3:1 input-to-output token ratio). Its specific pricing is $0.20 per 1M input tokens and $1.25 per 1M output tokens.

GPT-5.4 nano supports a context window of 400k tokens. This allows it to process large documents, codebase segments, or long chat histories in a single query session.

GPT-5.4 nano scores 52.4% on coding evaluations (SWE-bench-pro) and 81.7% on reasoning tasks (GPQA-diamond).

GPT-5.4 nano is an proprietary model developed by OpenAI.