Model · OpenRouter

Deepseek/DeepSeek V4 Flash 0423

Name: DeepSeek V4 Flash 0423
Author: Deepseek

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

View on OpenRouterReport an issue

Author / organization	Deepseek
Access	Hosted API (no weights listed here)
Price per million tokens	$0.091 in · $0.182 out
Context window	1,048,576 tokens
Task	text-generation
Created	24 April 2026
Last updated at source	—

text-generationhostedreasoningtool-use

Embed this entry

<iframe src="https://silytics.si/embed/item/4aa96127-4be1-4b66-9c42-cffe92e954c9" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Popularity, last 4 days

0 now. Counts as reported by the source, snapshotted daily by Silytics.

Price and speed history

USD per million tokens

InputOutput

More from Deepseek

Deepseek/DeepSeek V3.2 ExpModel
Deepseek/DeepSeek V3Model
Deepseek/DeepSeek V4 Flash Vision ExpModel
Deepseek/DeepSeek V3 0324Model
Deepseek/DeepSeek V4 Pro 0813Model
Deepseek/DeepSeek V3.1 TerminusModel

Silytics shows public metadata from OpenRouter and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.