DeepSeek V4 Flash 0731
Observed throughTokscale Model Report
DeepSeek V4 Flash 0731 model details and observed coding usage from Tokscale.
Reality Snapshot
Observed tokens
2.3B
over 30 days
Estimated tracked spend
$25
Invoices may differ
Active developers
21
this month
30-day momentum
—
Awaiting a prior 30-day window
Most-used client
OpenCode42%
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
96%cache read
Cache read2.2B96%
Input81.5M3.5%
Output7.1M<1%
Reasoning4.7M<1%
Cache-heavy workloadMost observed tokens reuse cached context across requests.
Observed Variants
via deepseek
deepseek/deepseek-v4-flash-07312B$23$0.0187.72%default
deepseek-v4-flash-0731253.3M$1.6$0.0010.94%via qwen-cloud
qwen-cloud/deepseek-v4-flash-073123.3M$0.3$0.011.01%via ali
ali/deepseek-v4-flash-07317.6M$0.1$0.010.33%via sekai
sekai/deepseek-v4-flash-073165.1K$0$0.140%fast
deepseek-v4-flash-0731-fast52.3K$0$0.170%Umans
umans-deepseek-v4-flash-07310$0$0.000%Token Economics
Estimated spend profile
OpenCode$9.7838.92%
Senpi$6.7826.99%
Pi$7.4729.72%
Hermes Agent$0.411.62%
Gajae-Code$0.000%
Codex CLI$0.311.24%
Cursor$0.230.93%
ZCode$0.050.21%
Observed cost signals
Estimated spend per 1M tracked tokens$0.01
Cache-read share96%
Estimated cache savingsNot available
Typical workloadcontext-heavy
Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.
Model Momentum
—30-day growthRank: Observed model
Awaiting a prior non-overlapping window
Fastest-growing client: OpenCode
Official Model Details
ProviderDeepseek
Tokscale Insight
DeepSeek V4 Flash 0731 recorded 2.3B coding tokens across 21 developers during the latest 30-day Tokscale window.
Observed confidenceHigh






