DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731

Developer	DeepSeek
Release date	July 31, 2026
Family	DeepSeek
Generation	DeepSeek V4
Level
Context window	1M tokens
Max output	944K tokens
Input	Text
Output	Text
Knowledge cutoff	2025-05
Weights	Open weights
License	MIT
Website	deepseek.com
Links	Model card Hugging Face

Part of a series on

input: $0.0434
cached: $0.035
output: $0.30
Context: 1Mtokens
Released: 3mo ago
Size: 304Bparameters

Specifications

Model

Developer: DeepSeek
Family: DeepSeek DeepSeek V4
Type: Language model
Released: July 31, 2026
Model ID: deepseek/deepseek-v4-flash-0731

Capabilities

Input → output: Text → Text
Max output: 944K tokens
Tokenizer: DeepSeek
Knowledge cutoff: 2025-05

Weights

Openness: Open weights
License: MIT
Size: 304B
Hugging Face: deepseek-ai/DeepSeek-V4-Flash-0731

Sources:models.devOpenRouter

Metadata synced Nov 10, 2026, 2:00 PM UTC

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