← Back to Directory

DeepSeek: DeepSeek V4 Flash 0731

DEEPSEEK Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1441Chatbot Arena Verified
Max Context1,048,576Tokens
API Cost / 1M$0.42Blended Prompt + Completion

Model Capabilities

  • Drafting
  • Classification
  • Vision
  • Coding & Logic
  • Fictional
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 (Prompt)$0.14 / 1M
Output Tokens (Completion)$0.28 / 1M

Pricing data via OpenRouter. Sync: 8/1/2026

Evaluate Competitors

VS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs Nex AGI: Nex-N2-MiniVS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs AllenAI: Olmo 3 32B ThinkVS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V3.1 TerminusVS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: o4 Mini HighVS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs Qwen2.5 Coder 32B InstructVS Engine MatchupDeepSeek: DeepSeek V4 Flash 0731 vs Cohere: North Mini Code (free)