Tokscale
Start Now
Menu

GPT-5.3-Codex

Observed through

Tokscale Model Report

GPT-5.3-Codex model details and observed coding usage from Tokscale.

Official details Browse models

Reality Snapshot

Observed tokens

698.9M-72.5%

over 30 days

Estimated tracked spend

$119

Invoices may differ

Active developers

15-22

this month

30-day momentum

-72.5%

Compared with the prior 30-day window

Most-used client

Cursor91%

of observed tokens

Observed Usage

Tokens observedDaily active developers
Observed coding tokens over 30 daysDaily observed usage from Jul 12 through Aug 10, with active developer activity for context.500M400M300M200M100M064.83.62.41.20Jul 12Jul 15Jul 18Jul 21Jul 24Jul 27Jul 29Aug 1Aug 4Aug 7Aug 10

How developers use it

Usage by coding client

Sharevs 30 days
Cursor
91%0%
OpenCode
4%0%
Hermes Agent
3%0%
Pi
1%0%

Token composition

Share of observed tokens

94%cache read
Cache read658.2M94%
Input37.7M5.4%
Output2.9M<1%
Reasoning72.1K<1%
Cache-heavy workloadMost observed tokens reuse cached context across requests.

Observed Variants

xhighgpt-5.3-codex-xhigh628.2M$91.3$0.1489.88%
defaultgpt-5.3-codex70.7M$27.8$0.3910.12%

Token Economics

Estimated spend profile

Cursor$9781.26%
OpenCode$119.12%
Hermes Agent$8.256.93%
Pi$2.692.26%
Copilot$0.480.4%
CodeBuddy$0.040.03%
OpenClaw$0.000%

Observed cost signals

Estimated spend per 1M tracked tokens$0.17
Cache-read share94.2%
Estimated cache savingsNot available
Typical workloadcontext-heavy

Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.

Model Momentum

-72.5%30-day growthRank: Observed model

Compared with the prior non-overlapping window

Fastest-growing client: Cursor

400M267M133M0Jul 12Jul 27Aug 10

Official Model Details

ProviderOpenAI

Tokscale Insight

GPT-5.3-Codex recorded 698.9M coding tokens across 15 developers during the latest 30-day Tokscale window.

Observed confidenceHigh