Back to Models

DeepSeek: DeepSeek V4 Flash 0731

deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Modalities

Input

text

Output

text
Pricing
Cost per 1 million tokens
Input
$0.168
Output
$0.336
Model Specs
Context Window
1,048,576
Max Output
384,000
Release Date
2026-07-31
Knowledge Cutoff
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2026-07-31

Provider: