TRENDING
Google Birthday 2026: How 28 Years of Search Led to the AI EraMuse AI Referral Code: Get 1 Billion Muse TokensClaude AI Found a New Enzyme System. Here's What Scientists KnowGoogle Just Gave Gemini a Face — Gemini 3.8 Live Avatar ExplainedGoogle's AI Agents Are Teaming Up to Make Longer VideosAustralia Investigates If OpenAI's AI Agent Broke the LawMeta Muse AI Glasses Explained: What's Real Right NowOpenAI's Agent Broke Into Australia's Medicare Site On Its OwnClaude Code Cloud Sessions: Claim Your $100 or $250 CreditAI Price War: Claude Opus 5.5 vs GPT-6 Sol and Luna ExplainedBristol Artists Criticize AI-Generated Mural After Visual ErrorsMeta Muse Zero-Day Explained: Can the AI Agent Be Hijacked?Claude Opus 5.5 Explained: Anthropic's New ModelJev AI Explained: The Decision Model That Returns Structured ChoicesAbhyas AI Explained: AI-Powered JEE & NEET Prep Platform

DeepSeek V4.1 Flash Released — Faster, Cheaper, and Better Than V4 Pro

⚡ Quick facts

  • New model launch: DeepSeek released V4.1 Flash on September 10, 2026, featuring a new architecture with native multimodal support and KV cache compression.
  • Beats V4 Pro: DeepSeek claims V4.1 Flash comprehensively surpasses V4 Pro across all key metrics — performance, cost, speed, and task completion time.
  • Cheaper pricing: Off-peak input costs start at $0.003 per cache hit unit, with output at $0.60 per unit — significantly cheaper than V4 Pro.
  • V4 Pro sunset: DeepSeek postponed V4 Pro discontinuation to September 14, 2026, after which all Pro requests reroute to V4.1 Flash.
  • Open weights: Model weights released on Hugging Face under the deepseek-ai organization, available via Vercel's AI Gateway.

Chinese AI lab DeepSeek has released V4.1 Flash, its latest large language model that the company says surpasses the previous V4 Pro across every major benchmark — while costing significantly less to run. Launched on September 10, 2026, the model introduces a new architecture built around KV cache compression, a technique that dramatically reduces the memory and compute required for inference.

What Is KV Cache Compression and Why Does It Matter?

When an AI model processes a conversation, it stores previous tokens in a "Key-Value cache" so it doesn't have to reprocess the entire conversation from scratch each time. The problem is that this cache grows linearly with conversation length, consuming expensive GPU memory.

DeepSeek V4.1 Flash's technical report — titled "Pushing Limits of KV Cache Compression" — describes how the new model compresses this cache far more aggressively than previous architectures. The result: faster inference speeds, lower memory requirements, and reduced cost per token — all without sacrificing output quality.

Performance: Surpassing V4 Pro on Every Metric

DeepSeek's official announcement states that V4.1 Flash "comprehensively surpassed V4 Pro across all key metrics, including performance, cost, speed, and task completion time." While specific benchmark numbers were not disclosed in the launch announcement, the company released a detailed technical report on Hugging Face for independent verification.

The model also features native multimodal support, meaning it can process both text and images natively rather than relying on separate encoder modules.

Pricing: How Much Does V4.1 Flash Cost?

DeepSeek has positioned V4.1 Flash as a cost leader in the frontier model market:

  • Input (cache hit): $0.003 per unit
  • Input (cache miss): $0.15 per unit
  • Output: $0.60 per unit
  • Peak hours (UTC 1“4 AM and 6“10 AM, Monday“Friday): Double the off-peak rates

For developers building on DeepSeek's API, the cache hit pricing is particularly notable — at $0.003 per unit, it is among the cheapest input costs of any frontier-class model available today.

V4 Pro Sunset: What Happens on September 14?

DeepSeek had originally planned to discontinue V4 Pro alongside the V4.1 Flash launch, but postponed the shutdown to September 14, 2026 at 12:00 Beijing Time. After that date:

  1. All API requests targeting V4 Pro will be automatically rerouted to V4.1 Flash
  2. Billing will switch to V4.1 Flash pricing (which is lower)
  3. No developer action is required — the transition is seamless

Where to Access V4.1 Flash

The model weights have been released on Hugging Face under the deepseek-ai/DeepSeek-V4.1-Flash repository. Developers can also access the model through Vercel's AI Gateway and DeepSeek's own API platform.

During the internal beta phase, DeepSeek limited the model to 20 concurrent requests per account — a constraint that may be relaxed as the model stabilizes in production.

Advertisement

Want to stay ahead of every new AI model release and pricing change? Follow AI Explainer India for timely, plain-English breakdowns of every major AI development that affects developers and businesses in India.

Related articles

Comments