DeepSeek V4 Flash 0423

DeepSeek V4 Flash 0423

Developer	DeepSeek
Release date	April 24, 2026
Family	DeepSeek
Generation	DeepSeek V4
Level
Context window	1M tokens
Max output	393K tokens
Input	Text
Output	Text
Knowledge cutoff	2025-05
Weights	Open weights
Successor	DeepSeek V4.1 Flash
Website	deepseek.com
Links	Model card Hugging Face

Part of a series on

input: $0.09
cached: $0.018
output: $0.18
Context: 1Mtokens
Released: 6mo ago
Size: 291Bparameters

Specifications

Model

Developer: DeepSeek
Family: DeepSeek DeepSeek V4
Type: Language model
Released: April 24, 2026
Model ID: deepseek/deepseek-v4-flash

Capabilities

Input → output: Text → Text
Max output: 393K tokens
Tokenizer: DeepSeek
Knowledge cutoff: 2025-05

Weights

Openness: Open weights
Size: 291B
Hugging Face: deepseek-ai/DeepSeek-V4-Flash

Sources:models.devOpenRouter

Metadata synced Nov 11, 2026, 2:00 AM UTC

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.