DeepSeek

DeepSeek V4 Flash

Name: DeepSeek V4 Flash
Brand: DeepSeek

Canonical ID: deepseek/deepseek-v4-flash

More DeepSeek models More v4-flash family models

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

Reasoning: Yes Tool use: Yes Open weights

Overview

text

Provider: DeepSeek
Family: v4-flash
Release date: 2026-04-28
Last updated: 2026-04-28
Input modalities: text
Output modalities: text

Pricing and Limits

Token pricing

Input: $0.14/1M
Output: $0.28/1M
Cached input: N/A

Context and output

Context window: 1,000,000
Max output tokens: 384,000
Qualified ID: deepseek/deepseek-v4-flash

Model Summary

DeepSeek V4 Flash is a model listing in the DeepSeek provider catalog. It is categorized under the v4-flash family.

The model supports text modalities across input/output paths. Reported context capacity is 1,000,000. Pricing is listed at $0.14/1M input and $0.28/1M output.

DeepSeek V4 Flash

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From DeepSeek

DeepSeek Chat

DeepSeek Reasoner

DeepSeek V4.1 Flash 1017

DeepSeek V4 Flash Vision Exp

DeepSeek V4 Pro