DeepSeek: DeepSeek V4 Flash 0731

DEEPSEEK Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1441Chatbot Arena Verified

Max Context Limit1,048,576Max Out: 943,718 tokens

Prompt CachingStandard$0.0051 / 1M cached

Standard API / 1M$1.29🧠 Deep Reasoner

Model Capabilities & Contract SLAs

Drafting
Classification
Vision
Reasoning
Coding & Logic
Fictional
🧠 Extended Test-Time Reasoning

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....

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.0051 / 1M

⚡ Cached Input (Prompt Cache Read)% OFF$0.0051 / 1M

Output Tokens (Completion)$1.28 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs Tencent: Hy-MT2-30B-A3B VS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V3.1 Terminus VS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: o4 Mini High VS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs Qwen2.5 Coder 32B Instruct VS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs Apodex: Apodex 1.1 Mini (free)VS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-6.1 Sol