DeepSeek: DeepSeek V4 Pro 0423

DEEPSEEK Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1592Chatbot Arena Verified

Max Context Limit1,048,576Max Out: 384,000 tokens

Prompt Caching92% OFF$0.02 / 1M cached

Standard API / 1M$0.63🧠 Deep Reasoner

Model Capabilities & Contract SLAs

Reasoning
Top Tier
Coding & Logic
Fictional
🧠 Extended Test-Time Reasoning

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.21 / 1M

⚡ Cached Input (Prompt Cache Read)92% OFF$0.02 / 1M

Output Tokens (Completion)$0.42 / 1M

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

Evaluate Competitors

VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0423 vs Anthropic: Claude Sonnet 5.5 (batch)VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0423 vs SpaceXAI: Grok 4.6 VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0423 vs SpaceXAI: Grok 4.7 VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0423 vs Anthropic: Claude Sonnet 5.5 VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0423 vs DeepSeek: DeepSeek V4 Pro 0813 VS Engine MatchupDeepSeek: DeepSeek V4 Pro 0423 vs Fireworks: Ember-1