Skip to content

GPT-5.4

ModelActive
by OpenAI · family “gpt”

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... (description from the OpenRouter listing)

in: textin: imagein: fileout: textReasoningTool useStructured output
Epoch Capabilities Index
156.9 #14 of 268
90% CI 155.1 – 159.3
Listing ↗
Released
5 Mar 2026
Context window
1.05M tokens
Max output
128K tokens
Input $ / 1M tokens
$2.50
Output $ / 1M tokens
$15.0
Cached input $ / 1M
$0.25
Each benchmark shown separately with its own source

Benchmark results (10)

BenchmarkDomainScorevs best recordedSettingRunSource
MirrorCodecoding15.6% ±7.7
20%
high10 Aug 2026Epoch ↗
CL-bench Lifelong-context19.3%
87%
high—External ↗
PostTrainBenchagents19.0%
45%
high—External ↗
Chess Puzzlesgames38.0% ±4.9
53%
high15 Jul 2026Eval log ↗
GSO-Benchcoding25.5%
54%
high—External ↗
ARC-AGI-2reasoning67.5%
71%
high—External ↗
OTIS Mock AIME 2024-2025math97.8% ±2.2
98%
high15 Jul 2026Eval log ↗
SWE-Bench verifiedcoding76.9% ±1.9
92%
high6 Mar 2026Eval log ↗
GPQA diamondscience89.9% ±2.1
94%
high15 Jul 2026Eval log ↗
ARC-AGIreasoning92.7%
94%
high—External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

7 recorded prices on 1 Apr 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 40m ago. Steps show when the price changed.

Events