Magica logo

DeepSeek V4 Flash 0423 Model Specs, Costs & Benchmarks (August 2026)

DeepSeek V4 Flash 0423, developed by DeepSeek, features a context window of 1M tokens. The model costs $0.14 per million tokens for input and $0.28 per million tokens for output. It was released on April 24, 2026, and has achieved impressive scores in various benchmarks.
Access DeepSeek V4 Flash 0423 & 210+ other AI models all in one platformTry Magica for free

Overview

DeepSeek V4 Flash 0423DeepSeek V4 Flash 0423
Model Provider
The organization behind this AI's development
DeepSeek logoDeepSeek
Input Context Window
Maximum input tokens this model can process at once
1M
tokens
Output Token Limit
Maximum output tokens this model can generate at once
393.2K
tokens
Release Date
When this model first became publicly available
April 24th, 2026

Pricing

DeepSeek V4 Flash 0423DeepSeek V4 Flash 0423
Input Token Cost
Cost per million input tokens
$0.14
per million tokens
Output Token Cost
Cost per million output tokens
$0.28
per million tokens
Cache Read Cost
Cost to reuse cached input tokens
$0.03
per million tokens

Capabilities & Features

DeepSeek V4 Flash 0423DeepSeek V4 Flash 0423
Input Types
Supported input formats
text
Output Types
Supported output formats
text
Tokenizer
Text encoding system
DeepSeek
Key Features
Advanced capabilities
βœ“ Function Callingβœ“ Structured Outputβœ“ Reasoning Mode
Reasoning Controls
Defaults and configurable reasoning effort
OptionalEffort: Extra High, HighDefault: High
Open Source
Model availability

Benchmarks

DeepSeek V4 Flash 0423DeepSeek V4 Flash 0423
Best Design Arena Score
Highest human-preference Elo score across design arenas
1,242 Elo
(#37 in 3D (49.3% win rate))