DeepSeek: DeepSeek V4 Flash

DEEPSEEK Developer Architecture Profile

Intelligence (ELO)1437Chatbot Arena Verified

Max Context1,048,576Tokens

API Cost / 1M$0.42Blended Prompt + Completion

Model Capabilities

Drafting
Classification
Coding & Logic
Fictional

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...

Granular Pricing Matrix

Input Tokens (Prompt)$0.14 / 1M

Output Tokens (Completion)$0.28 / 1M

Pricing data via OpenRouter. Sync: 4/24/2026

Evaluate Competitors

VS Engine MatchupDeepSeek: DeepSeek V4 Flash vs Qwen: Qwen3.5-27B VS Engine MatchupDeepSeek: DeepSeek V4 Flash vs Qwen: Qwen3 Next 80B A3B Instruct (free)VS Engine MatchupDeepSeek: DeepSeek V4 Flash vs Mistral Large 2407 VS Engine MatchupDeepSeek: DeepSeek V4 Flash vs WizardLM-2 8x22B VS Engine MatchupDeepSeek: DeepSeek V4 Flash vs MiniMax: MiniMax M2.7 VS Engine MatchupDeepSeek: DeepSeek V4 Flash vs Mistral: Mistral Small 4