Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
Specification
most-agreed values
Context
1M
Max output
384K
Released
2026-07-31
Knowledge cutoff
2025-05
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.4453
Output
$1.3359
Cache read
$0.0148
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| volcengine | $0.4453 | $1.3359 | $0.0148 | — | 1M | 384K | — |
Other listings of this model
this page is one of them
The corpus files DeepSeek V4 Flash 0731 under several keys. This page is the deepseek-v4-flash-ga-260731 listing. The full record — every host, every price and every benchmark score — is on the main DeepSeek V4 Flash 0731 page.
More from DeepSeek
most-hosted first