Tokscale
Open console
Menu

Gpt 5 3 Codex Spark

Observed through

Tokscale Model Report

Gpt 5 3 Codex Spark model details and observed coding usage from Tokscale.

Official details Browse models

Reality Snapshot

Observed tokens

11.5B-4.8%

over 30 days

Estimated tracked spend

$4.4K

Invoices may differ

Active developers

137-62

this month

30-day momentum

-4.8%

Compared with the prior 30-day window

Most-used client

Codex CLI66%

of observed tokens

Observed Usage

Tokens observedDaily active developers
Observed coding tokens over 30 daysDaily observed usage from Jun 30 through Jul 29, with active developer activity for context.1.5B1.2B900M600M300M050403020100Jun 30Jul 3Jul 6Jul 9Jul 12Jul 15Jul 17Jul 20Jul 23Jul 26Jul 29

How developers use it

Usage by coding client

Sharevs 30 days
Codex CLI
66%0%
Pi
20%0%
OpenCode
13%0%
Claude Code
1%0%
OpenClaw
<1%0%
Hermes Agent
<1%0%

Token composition

Share of observed tokens

93%cache read
Cache read10.7B93%
Input702.4M6.1%
Output62.3M<1%
Reasoning32.3M<1%
Cache-heavy workloadMost observed tokens reuse cached context across requests.

Token Economics

Estimated spend profile

Codex CLI$2.7K61.99%
Pi$80718.26%
OpenCode$81118.34%
Claude Code$511.14%
OpenClaw$8.210.19%
Hermes Agent$3.420.08%
Goose$0.020%
Grok Build$0.010%

Observed cost signals

Estimated spend per 1M tracked tokens$0.39
Cache-read share93%
Estimated cache savingsNot available
Typical workloadcontext-heavy

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

Model Momentum

-4.8%30-day growthRank: Observed model

Compared with the prior non-overlapping window

Fastest-growing client: Codex CLI

1.5B1B500M0Jun 30Jul 15Jul 29

Official Model Details

ProviderOpenAI

Tokscale Insight

Gpt 5 3 Codex Spark recorded 11.5B coding tokens across 137 developers during the latest 30-day Tokscale window.

Observed confidenceHigh