GPT-5.4 (Non-reasoning)

OpenAI·Released 2026-03-05

Compare

Quality Index

35.4

69th of 440

Top 16%

Coding Index

41.0

25th of 350

Top 7%

Price/1M

$5.63

627th cheapest

1715% above median

Top 93%

Speed

57 tok/s

Top 43%

TTFT

0.66s

Market Position

GPT-5.4 (Non-reasoning)Market Average

Pricing

Input

$2.50

per 1M tokens

Output

$15.00

per 1M tokens

Blended

$5.63

per 1M tokens

Cheaper than 7% of models. Median price is $0.31/1M tokens.

Cost Calculator

Tokens per day1M

100K100M

Daily

$5.63

Monthly

$168.75

vs. Similar Models

Grok 4 Fast (Reasoning)Q:-0.3

$0.28-95%

Nova 2.0 Pro Preview (medium)Q:+0.3

$3.44-39%

Gemini 3 Flash Preview (Non-reasoning)Q:-0.4

$1.13-80%

Qwen3.5 122B A10B (Non-reasoning)Q:+0.5

$1.10-80%

Performance

57

tokens/sec

Faster than 57% of models

0.66

seconds

Faster than 38% of models

Market Median

46 tok/s

25% faster

Median TTFT

0.43s

54% slower

Throughput/Dollar

10

tok/s per $/1M

Speed Comparison

Qwen3 VL 235B A22B Instruct

57 tok/s-0%

Pixtral Large

57 tok/s+0%

GLM-4.6 (Non-reasoning)

57 tok/s+0%

Benchmarks

MMLU-ProNot evaluated

GPQA Diamond

74.8%

HLE

10.6%

LiveCodeBenchNot evaluated

SciCode

47.1%

TerminalBench Hard

37.9%

MATH-500Not evaluated

AIMENot evaluated

AIME 2025Not evaluated

IFBench

48.4%

Long Context Recall

47.3%

Tau2

35.1%

Market AverageTop Score

Quick Compare

Similar Models

Grok 4 Fast (Reasoning)

xAI

Q: 35.1$0.28/1M

Faster: 146%Cheaper: 95%

Nova 2.0 Pro Preview (medium)

Amazon

Q: 35.7$3.44/1M

Faster: 146%Cheaper: 39%

Gemini 3 Flash Preview (Non-reasoning)

Google

Q: 35.0$1.13/1M

Faster: 246%Cheaper: 80%

Qwen3.5 122B A10B (Non-reasoning)

Alibaba

Q: 35.9$1.10/1M

Faster: 157%Cheaper: 80%

NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

NVIDIA

Q: 36.0$0.41/1M

Faster: 647%Cheaper: 93%

KAT-Coder-Pro V1

KwaiKAT

Q: 36.0$0.53/1M

Cheaper: 91%Coding: -22.7

Compare all 7 models