GPT-5.4 (Non-reasoning)

OpenAIUnited States

GPT-5.4 (Non-reasoning) is a high-performance, general-purpose model optimized for speed and cost-efficiency. It delivers strong core capabilities in coding, multimodal understanding, and long-context processing without the overhead of advanced reasoning or chain-of-thought features, making it ideal for high-throughput applications.

CodingFastCheapLong contextMultimodal

Input / 1M tokens

$2.50

Output / 1M tokens

$15.00

Output tokens/s

63.47

First-token seconds

0.71s

Supported plans

Benchmark history

Evaluations

TAU2

Measured May 14, 2026Source

Score

0.35

Terminalbench Hard

Measured May 14, 2026Source

Score

0.38

Lcr

Measured May 14, 2026Source

Score

0.47

Ifbench

Measured May 14, 2026Source

Score

0.48

Scicode

Measured May 14, 2026Source

Score

0.47

Hle

Measured May 14, 2026Source

Score

0.11

Gpqa

Measured May 14, 2026Source

Score

0.75

Artificial Analysis Coding Index

Measured May 14, 2026Source

Score

Artificial Analysis Intelligence Index

Measured May 14, 2026Source

Score

35.4

Plan availability

Products and plans that support this model

No products or plans have been linked to this model yet.

Discussion

Thinking... Make sure you are connected to GitHub server