modelbenchmark.io

GPT-5.3 Codex

OpenAI · gpt-5-3-codex

Compare

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Specification

openai listing

Context
400K
Max output
128K
Released
2026-02-05
Knowledge cutoff
2025-08-31
Retires
2027-04-01
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · openai list price

Input
$1.75
Output
$14.00
Cache read
$0.175
Cache write
$1.75

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Priority inputazure$3.50
Priority inputazure$3.85
Priority outputazure$28.00
Priority outputazure$30.80

Quality

1 benchmark · 1 source

Composite
90th
percentile of 344 scored models
Rank
37 / 344
±0.10 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
coding79th1/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SWE-Bench verified74.8 ±2.0defaultEpoch AI2026-02-25

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

Available from 34 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$1.75$14.00$0.175—
400K
272K
128K2027-04-01
poe$1.5909$12.7273$0.1591—400K128K—
abacus$1.75$14.00$0.175—400K128K—
aihubmix$1.75$14.00$0.175—400K128K—
aihubmix · aihubmix$1.75$14.00$0.175—400K128K—
azure
$1.75
$1.925
$14.00
$15.40
$0.175
$0.1925
—
400K
272K
128K2027-08-24
azure-cognitive-services$1.75$14.00$0.175—400K128K—
databricks$1.75$14.00$0.175$1.75272K128K—
edenai$1.75$14.00$0.175—400K128K—
fastrouter$1.75$14.00$0.175—400K128K—
freemodel$1.75$14.00$0.175$1.75400K128K—
frogbot$1.75$14.00$0.175—400K128K—
github_copilot · github-copilot$1.75$14.00$0.175—128K128K—
github-copilot$1.75$14.00$0.175—400K128K—
impossibl$1.75$14.00$0.175—400K128K—
kilo$1.75$14.00$0.175—400K128K—
llmgateway$1.75$14.00$0.175—400K128K—
llmgateway-providers$1.75$14.00$0.175—400K128K—
nano-gpt$1.75$14.00$0.175—400K128K—
neon$1.75$14.00$0.175—400K128K—
ofox$1.75$14.00$0.18—400K128K—
opencode$1.75$14.00$0.175—400K128K—
openrouter$1.75$14.00$0.175—400K128K—
opper$1.75$14.00$0.175—400K128K—
orcarouter$1.75$14.00$0.175—400K128K—
prime$1.75$14.00——400K128K—
requesty$1.75$14.00$0.175—400K128K—
vercel$1.75$14.00$0.175—400K128K—
vivgrid$1.75$14.00$0.175—400K128K—
zenmux$1.75$14.00$0.175—400K128K—
commandcode$2.00$8.00$0.50free400K128K—
perplexity$3.50$28.00$0.35————
aimlapi$3.703$29.624$0.3703—400K128K—
chatgpt · chatgpt————128K128K—

Price history

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

DateHostField$/M
2026-09-02abacusCache read$0.18
2026-10-22abacusCache read$0.175
2026-09-02azureCache read$0.175
2026-09-17azureCache read$0.175
2026-09-02ofoxCache read$0.18
2026-09-19ofoxCache read$0.144
2026-10-17ofoxCache read$0.18
2026-09-02openrouterCache read$0.175
2026-09-06openrouterCache read$0.175
2026-10-10openrouterCache read$0.175
2026-09-02poeCache read$0.16
2026-10-22poeCache read$0.1591
2026-09-02azureInput$1.75
2026-09-17azureInput$1.75
2026-09-02ofoxInput$1.75
2026-09-19ofoxInput$1.40
2026-10-17ofoxInput$1.75
2026-09-02openrouterInput$1.75
2026-09-06openrouterInput$1.75
2026-10-10openrouterInput$1.75
2026-09-02poeInput$1.60
2026-10-22poeInput$1.5909
2026-09-02azureOutput$14.00
2026-09-17azureOutput$14.00
2026-09-02ofoxOutput$14.00
2026-09-19ofoxOutput$11.20
2026-10-17ofoxOutput$14.00
2026-09-02openrouterOutput$14.00
2026-09-06openrouterOutput$14.00
2026-10-10openrouterOutput$14.00
2026-09-02poeOutput$13.00
2026-10-22poeOutput$12.7273
2026-10-13aimlapiCache read$0.4814
2026-10-23aimlapiCache read$0.3703
2026-10-13aimlapiInput$4.8139
2026-10-23aimlapiInput$3.703
2026-10-13aimlapiOutput$38.5112
2026-10-23aimlapiOutput$29.624

Other listings of this model

same model, different key

More from OpenAI

most-hosted first