← Back to Directory

DeepSeek: DeepSeek V4 Pro 0813

DEEPSEEK Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1608Chatbot Arena Verified
Max Context Limit1,048,576Max Out: 393,216 tokens
Prompt Caching97% OFF$0.02 / 1M cached
Standard API / 1M$2.64Blended Standard Rate

Model Capabilities & Contract SLAs

  • Top Tier
  • Coding & Logic
  • Fictional
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.66 / 1M
⚡ Cached Input (Prompt Cache Read)97% OFF$0.02 / 1M
Output Tokens (Completion)$1.98 / 1M

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

Evaluate Competitors

VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0813 vs Anthropic: Claude Sonnet 5.5VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0813 vs SpaceXAI: Grok 4.7VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0813 vs Anthropic: Claude Sonnet 5.5 (batch)VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0813 vs SpaceXAI: Grok 4.6VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0813 vs DeepSeek: DeepSeek V4 Pro 0423