DeepSeek Reasoner
Observed throughTokscale Model Report
DeepSeek Reasoner model details and observed coding usage from Tokscale.
Reality Snapshot
Observed tokens
1.1B+125.7%
over 30 days
Estimated tracked spend
$5.85
Invoices may differ
Active developers
4+1
this month
30-day momentum
+125.7%
Compared with the prior 30-day window
Most-used client
Hermes Agent99%
of observed tokens
Observed Usage
Tokens observedDaily active developers
How developers use it
Usage by coding client
Sharevs 30 daysToken composition
Share of observed tokens
98%cache read
Cache read1.1B98%
Input19.8M1.8%
Output2.5M<1%
Reasoning62.6K<1%
Cache-heavy workloadMost observed tokens reuse cached context across requests.
Token Economics
Estimated spend profile
Hermes Agent$5.7598.23%
OpenCode$0.091.52%
ZCode$0.010.25%
Observed cost signals
Estimated spend per 1M tracked tokens$0.01
Cache-read share98%
Estimated cache savingsNot available
Typical workloadcontext-heavy
Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.
Model Momentum
+125.7%30-day growthRank: Observed model
Compared with the prior non-overlapping window
Fastest-growing client: Hermes Agent
Official Model Details
ProviderDeepseek
Tokscale Insight
DeepSeek Reasoner recorded 1.1B coding tokens across 4 developers during the latest 30-day Tokscale window.
Observed confidenceLimited sample

