DeepSeek: DeepSeek V4.1 Flash

DEEPSEEK Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1428Chatbot Arena Verified

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

Prompt Caching98% OFF$0.0060 / 1M cached

Standard API / 1M$1.50Blended Standard Rate

Model Capabilities & Contract SLAs

Drafting
Classification
Coding & Logic
Fictional

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.30 / 1M

⚡ Cached Input (Prompt Cache Read)98% OFF$0.0060 / 1M

Output Tokens (Completion)$1.20 / 1M

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

Evaluate Competitors

VS Engine MatchupDeepSeek: DeepSeek V4.1 Flash vs Anthropic: Claude Haiku Latest VS Engine MatchupDeepSeek: DeepSeek V4.1 Flash vs Morph: Morph V3 Large VS Engine MatchupDeepSeek: DeepSeek V4.1 Flash vs inclusionAI: Ling 3.0 Flash VL VS Engine MatchupDeepSeek: DeepSeek V4.1 Flash vs Nex AGI: Nex-N2.5-Mini VS Engine MatchupDeepSeek: DeepSeek V4.1 Flash vs Thinking Machines: Inkling Small VS Engine MatchupDeepSeek: DeepSeek V4.1 Flash vs SpaceXAI: Grok 4.3