Model dossier

DeepSeek: 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.

ProviderDeepSeek Start comparison

Context1,048,576

Max output384,000

Pricing viewTVP price

Identity

DeepSeek: DeepSeek V4 Flash 0731

Model ID: deepseek/deepseek-v4-flash-0731
Canonical slug: deepseek/deepseek-v4-flash-20260731
Knowledge cutoff: n/a
Created: 7/31/2026

Capabilities

texttoolsstructured

Modalities

text->texttext

Capacity

Context1,048,576

Max output384,000

TokenizerDeepSeek