DeepSeek V4 Flash 0423
DeepSeek V4 Flash is an AI model from DeepSeek, released with open weights.
Cite
Notes
Only stored in your browser.
Context
1.0M
Weights
Open
downloadable
Input
$0.11
/1M tok
Output
$0.23
/1M tok
Cache read
$0.01
0.13x input
Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter
| Reasoning effort | Index | Price | Speed |
|---|---|---|---|
| max | 24.2 | $0.14 | 0 t/s |
| high | 24.4 | $0.14 | 0 t/s |
| Non-reasoning | 18.9 | $0.12 | 0 t/s |
Intelligence Index per reasoning-effort setting, via Artificial Analysis
Reported on 19 evals across 7 domains - best 95.0% on τ²-bench (Tau²-bench) · #23 of 321