modelbenchmark.io

GPT-5.4 mini

OpenAI · gpt-5-4-mini

Compare

Strong small GPT for coding subagents, quick tool use, and high-volume work

Specification

openai listing

Context
400K
Max output
128K
Released
2026-03-17
Knowledge cutoff
2025-08-31
Retires
2027-09-21
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · openai list price

Input
$0.75
Output
$4.50
Cache read
$0.075
Cache write
$0.75

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputazure$0.375
Batch inputazure$0.4125
Batch outputazure$2.25
Batch outputazure$2.475
Priority inputazure_ai$1.50
Priority inputazure$1.65
Priority outputazure_ai$9.00
Priority outputazure$9.90

Batch input is 50% below the interactive input price at the same listing.

Quality

10 benchmarks · 2 sources

Composite
47th
percentile of 344 scored models
Rank
184 / 344
±0.07 sd
Evidence
10 × 2
3 or more benchmarks, from 2 or more sources
Effort range
3.3
points between effort settings
reasoning53rd3/4 bench
math54th5/7 bench
knowledge23rd1/1 bench
general8th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
high64th6
xhigh51st6
low21st2
medium20th1

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
OTIS Mock AIME 2024-202588.9 ±4.7xhighEpoch AI2026-08-07
↳87.2 ±4.3highEpoch AI2026-04-15
Settings differ by 1.7 points on this benchmark.
GPQA diamond86.9 ±2.4xhighEpoch AI2026-08-07
↳83.6 ±2.2highEpoch AI2026-04-15
Settings differ by 3.3 points on this benchmark.
FrontierMath-v139.1 ±16.7high · 2 runsEpoch AI2026-04-15
FrontierMath-Tiers-1-3-v251.2 ±3.0xhighEpoch AI2026-06-12
↳24.6 ±2.6lowEpoch AI2026-08-28
Settings differ by 26.6 points on this benchmark.
FrontierMath-Tier-4-2025-07-012.1 ±2.1highEpoch AI2026-04-15
Chess Puzzles23.0 ±4.2highEpoch AI2026-10-13
↳17.0 ±3.8xhighEpoch AI2026-10-13
Settings differ by 6.0 points on this benchmark.
SimpleQA Verified29.4 ±1.4highEpoch AI2026-08-27
Mystery Game Puzzles8.0 ±2.7lowEpoch AI2026-08-27
↳7.0 ±2.6mediumEpoch AI2026-08-27
Settings differ by 1.0 points on this benchmark.
FrontierMath-Tier-4-v29.8 ±4.7xhighEpoch AI2026-06-12
LiveBench66.6xhigh · 23 runsLiveBench2026-06-25

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 43 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$0.75$4.50$0.075—
400K
272K
128K—
xpersona$0.375$4.00$0.0375—272K128K—
poe$0.6818$4.0909$0.0682—400K128K—
302ai$0.75$4.50$0.075—400K128K—
abacus$0.75$4.50$0.075—400K128K—
aihubmix$0.75$4.50$0.075—400K128K—
aihubmix · aihubmix$0.75$4.50$0.075—400K128K—
azure
$0.75
$0.825
$4.50
$4.95
$0.075
$0.0825
—
400K
272K
128K2027-09-21
azure_ai$0.75$4.50$0.075—272K128K2027-09-21
azure-cognitive-services$0.75$4.50$0.075—400K128K—
cloudflare-ai-gateway$0.75$4.50$0.075—128K128K—
commandcode$0.75$4.50$0.075free400K128K—
crossmodel$0.75$4.50$0.075$0.75400K128K—
databricks$0.75$4.50$0.075$0.75
400K
272K
128K—
edenai$0.75$4.50$0.075—400K128K—
fastrouter$0.75$4.50$0.075—400K128K—
freemodel$0.75$4.50$0.075$0.75400K128K—
frogbot$0.75$4.50$0.075—400K128K—
github_copilot · github-copilot$0.75$4.50$0.075—272K128K2026-10-19
github-copilot$0.75$4.50$0.075—400K128K—
impossibl$0.75$4.50$0.075—400K128K—
kilo$0.75$4.50$0.075—400K128K—
llmgateway$0.75$4.50$0.075—400K128K—
llmgateway-providers$0.75$4.50$0.075—400K128K—
lowrouter · auto$0.75$4.50$0.075—400K128K—
merge-gateway$0.75$4.50$0.075—400K128K—
nano-gpt$0.75$4.50$0.075—400K128K—
nearai$0.75$4.50$0.075—400K128K—
neon$0.75$4.50$0.075—400K128K—
ofox$0.75$4.50$0.075—400K128K—
opencode$0.75$4.50$0.075—400K128K—
openrouter$0.75$4.50$0.075—400K128K—
opper$0.75$4.50$0.075—400K128K—
orcarouter$0.75$4.50$0.075—400K128K—
perplexity$0.75$4.50$0.075————
prime$0.75$4.50——400K128K—
requesty$0.75$4.50$0.075—400K128K—
vercel$0.75$4.50$0.075—400K128K—
vivgrid$0.75$4.50$0.075—400K128K—
zenmux$0.75$4.50$0.075—400K128K—
kenari$0.8571$5.3714——400K128K—
aimlapi$1.587$9.522$0.1587—400K128K—
model-oracle-ai————400K128K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02azureCache read$0.075
2026-09-17azureCache read$0.075
2026-09-02ofoxCache read$0.075
2026-09-19ofoxCache read$0.06
2026-10-17ofoxCache read$0.075
2026-09-02openrouterCache read$0.075
2026-09-06openrouterCache read$0.075
2026-10-10openrouterCache read$0.075
2026-09-02poeCache read$0.068
2026-10-22poeCache read$0.0682
2026-09-02azureInput$0.75
2026-09-17azureInput$0.75
2026-09-02kenariInputfree
2026-10-22kenariInput$0.8571
2026-09-02ofoxInput$0.75
2026-09-19ofoxInput$0.60
2026-10-17ofoxInput$0.75
2026-09-02openrouterInput$0.75
2026-09-06openrouterInput$0.75
2026-10-10openrouterInput$0.75
2026-09-02poeInput$0.68
2026-10-22poeInput$0.6818
2026-09-02azureOutput$4.50
2026-09-17azureOutput$4.50
2026-09-02kenariOutputfree
2026-10-22kenariOutput$5.3714
2026-09-02ofoxOutput$4.50
2026-09-19ofoxOutput$3.60
2026-10-17ofoxOutput$4.50
2026-09-02openrouterOutput$4.50
2026-09-06openrouterOutput$4.50
2026-10-10openrouterOutput$4.50
2026-09-02poeOutput$4.00
2026-10-22poeOutput$4.0909
2026-10-13aimlapiCache read$0.2063
2026-10-23aimlapiCache read$0.1587
2026-10-13aimlapiInput$2.0631
2026-10-23aimlapiInput$1.587
2026-10-13aimlapiOutput$12.3786
2026-10-23aimlapiOutput$9.522

Other listings of this model

same model, different key

More from OpenAI

most-hosted first