modelgrep
O

OpenAI: GPT-5.4

openai/gpt-5.4

4th smartest of 178ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
56.8
4th of 178
Design Elo
1303
Game Dev
Speed
62
132nd fastest
Latency
982ms
first token
Input price
$2.50
252nd cheapest
Context
1.1M
128K max out

How it compares

Smarter than98%
of all ranked models
Faster than55%
of all ranked models
Cheaper than15%
of all ranked models

Overview

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

Benchmarks

independent · via OpenRouter
Artificial Analysis98th percentile
Intelligence Index
56.8
Coding Index
57.2
Agentic Index
68.0
GPQA Diamond
92%
Humanity's Last Exam
42%
SciCode
57%
Tau²-Bench (agentic)
87%
Design Arena · Elo8,347 tournaments
Website
1269
codecategories
1267
UI Component
1259
Game Dev
1257
asciiart
1236
Data Viz
1222
svg
1180
godotgamedev
1173
mobileapps
1161
webapps
1153
3D
1124
fullstack
1097
androidnative
1047

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
OpenAI$2.50$15.0099.5%
Azure$2.50$15.00100%

Specifications

Context window1.1M
Max output128K
Knowledge cutoff
Input modalitiestext, image, file
Output modalitiestext
Prompt caching
Cache read price$0.250/M
ModeratedYes

GPT-5.4 FAQ

How much does GPT-5.4 cost?

GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens via OpenRouter, making it 252nd cheapest of 298 paid models.

How smart is GPT-5.4?

GPT-5.4 scores 56.8 on the Artificial Analysis Intelligence Index, ranking 4th of 178 benchmarked models, with a GPQA Diamond score of 92%.

How fast is GPT-5.4?

GPT-5.4 generates around 62 tokens per second with 982ms time-to-first-token (p50), the 132nd fastest tracked model.

What is GPT-5.4's context window?

GPT-5.4 supports a 1.1M-token context window and can output up to 128K tokens. It accepts text, image, file input.

Compare head-to-head