Model dossier

DeepSeek: DeepSeek V4 Flash

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...

ProviderDeepSeek Start comparison

Context1,048,576

Max output65,536

Pricing viewTVP price

Identity

DeepSeek: DeepSeek V4 Flash

Model ID: deepseek/deepseek-v4-flash
Canonical slug: deepseek/deepseek-v4-flash-20260423
Knowledge cutoff: n/a
Created: 4/24/2026

Capabilities

texttoolsstructured

Modalities

text->texttext

Capacity

Context1,048,576

Max output65,536

TokenizerDeepSeek