GPT-5.4 Mini
Observed throughTokscale Model Report
GPT-5.4 Mini model details and observed coding usage from Tokscale.
Reality Snapshot
Observed tokens
12.4B-72.4%
over 30 days
Estimated tracked spend
$2.6K
Invoices may differ
Active developers
166-186
this month
30-day momentum
-72.4%
Compared with the prior 30-day window
Most-used client
OpenCode55%
of observed tokens
Observed Usage
Tokens observedDaily active developers
How developers use it
Usage by coding client
Sharevs 30 days
Token composition
Share of observed tokens
88%cache read
Cache read10.9B88%
Input1.3B11%
Output94.9M<1%
Reasoning85M<1%
Cache-heavy workloadMost observed tokens reuse cached context across requests.
Observed Variants
default
gpt-5.4-mini8B$1.7K$0.2164.33%fast
gpt-5.4-mini-fast4.4B$892.9$0.2035.66%via cx
cx/gpt-5.4-mini275.1K$0.1$0.300%router via codex
router_client:codex/gpt-5.4-mini225.2K$0$0.000%via openai
openai/gpt-5.4-mini0$0$0.000%Token Economics
Estimated spend profile
OpenCode$1.4K51.91%
Codex CLI$1.2K45.39%
Pi$341.29%
Hermes Agent$361.37%
OpenClaw$0.390.01%
Claude Code$0.320.01%
Jcode$0.220.01%
Synthetic$0.000%
Observed cost signals
Estimated spend per 1M tracked tokens$0.21
Cache-read share87.9%
Estimated cache savingsNot available
Typical workloadcontext-heavy
Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.
Model Momentum
-72.4%30-day growthRank: Observed model
Compared with the prior non-overlapping window
Fastest-growing client: OpenCode
Official Model Details
ProviderOpenAI
Tokscale Insight
GPT-5.4 Mini recorded 12.4B coding tokens across 166 developers during the latest 30-day Tokscale window.
Observed confidenceHigh