DeepSeek V4 Flash 0423
Open weights
DeepSeek V4 Flash is an AI model from DeepSeek, released with open weights.
Cite
Notes
Only stored in your browser.
Context
1.0M
Input
$0.13
/1M tok
Output
$0.28
/1M tok
Blended
$0.17
#234/ 461/1M · 3:1
Speed
0
#115/ 461tok/s
Cache read
$0.02
0.12x input
Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter
| Reasoning effort | Index | Price | Speed |
|---|---|---|---|
| Reasoning, max | 42.1 | $0.17 | 0 t/s |
| Reasoning, high | 39.0 | $0.17 | 0 t/s |
| Non-reasoning | 29.3 | $0.12 | 0 t/s |
Intelligence Index per reasoning-effort setting, via Artificial Analysis
Reported on 19 evals across 7 domains - best 94.4% on τ²-bench (Tau²-bench) · #16 of 321