whichllmmodel
Back to Dashboard
💬 Text ModelProprietary

GPT-5.4

by OpenAI

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

Benchmark Evaluations

Codingswe-bench-pro

57.7%

Reasoninggpqa-diamond

92.8%

Pricing & Speed Details

Input Cost

$2.50

per 1M tokens
Output Cost

$15.00

per 1M tokens
Blended Cost

$5.63

based on 3:1 ratio
Speed

74 tps

Context Window

1.05M tokens

Want to test this model?

Compare GPT-5.4 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 has a blended cost of $5.63 per 1 million tokens (calculated using a standard 3:1 input-to-output token ratio). Its specific pricing is $2.50 per 1M input tokens and $15.00 per 1M output tokens.

GPT-5.4 supports a context window of 1.05M tokens. This allows it to process large documents, codebase segments, or long chat histories in a single query session.

GPT-5.4 scores 57.7% on coding evaluations (SWE-bench-pro) and 92.8% on reasoning tasks (GPQA-diamond).

GPT-5.4 is an proprietary model developed by OpenAI.