DeepSeek V4 Preview: MIT Open Weights and 1M Context

DeepSeek released V4-Pro and V4-Flash in preview on April 24, 2026, with MIT-licensed weights and a one-million-token context window.

Two models, one new base architecture

DeepSeek released preview versions of two models on April 24, 2026: DeepSeek-V4-Pro, a mixture-of-experts model with 1.6 trillion total parameters and 49 billion active per token, and DeepSeek-V4-Flash, a smaller sibling with 284 billion total parameters and 13 billion active. Both ship as open weights on Hugging Face under the MIT license, both default to a one million token context window, and both run in a thinking or non-thinking mode through the same API.

DeepSeek described the release as an upgrade path rather than a parallel option: existing API callers only need to change the model name to deepseek-v4-pro or deepseek-v4-flash, and the older deepseek-chat and deepseek-reasoner endpoints are scheduled for retirement on July 24, 2026.

A new attention mechanism built for the million-token context

The architectural change centers on the attention mechanism. Where V3.2 added DeepSeek Sparse Attention on top of V3's Multi-head Latent Attention, the V4 models replace both with a hybrid scheme the Hugging Face model card describes as Compressed Sparse Attention paired with Heavily Compressed Attention, along with Manifold-Constrained Hyper-Connections strengthening the residual path across layers and a switch to the Muon optimizer for training stability.

DeepSeek's efficiency claim for the new mechanism is specific to long context: at the million-token mark, V4-Pro needs 27 percent of the single-token inference compute and 10 percent of the key-value cache that V3.2 required. V4-Pro trained on more than 32 trillion tokens, with the report describing separate post-training passes for different domains that were later merged into one model.

Back near the front of the open-weight pack, with a caveat

Independent benchmarking from Artificial Analysis put V4-Pro at 52 on its Intelligence Index, the second-highest score among open-weight reasoning models at the time, behind only Moonshot AI's Kimi K2.6. V4-Flash scored 47, in the range of Anthropic's Claude Sonnet 4.6 at maximum reasoning effort. On GDPval-AA, an agentic benchmark, V4-Pro's score of 1554 led every open-weight model tested, ahead of Kimi K2.6's 1484.

The same testing turned up a sharp limitation: both models answer even when they do not know, at a hallucination rate of 94 percent for V4-Pro and 96 percent for V4-Flash on the questions Artificial Analysis used to measure it. A model can score well on reasoning benchmarks and still be an unreliable source of unverified facts, and this release's own numbers illustrate that gap directly rather than as a general caveat about the category.

Priced under the frontier labs, covered as a return to form

API pricing undercuts the closed-source frontier: Artificial Analysis lists V4-Pro at $1.74 per million input tokens and $3.48 per million output tokens, and V4-Flash at $0.14 and $0.28. Both models are text-only, with no image, audio or video input or output, unlike some closed frontier competitors.

TechCrunch covered the release as DeepSeek narrowing, though not closing, the gap with frontier labs, citing DeepSeek's own comparisons showing V4-Pro ahead of GPT-5.2 and Gemini 3.0 Pro on some reasoning tasks, roughly level with GPT-5.4 on coding competitions, and trailing GPT-5.4 and Gemini 3.1 Pro on knowledge tests by what the outlet described as three to six months of development.

This is DeepSeek's first release to draw sustained comparison to the open-weight leaders again since R1 set off a market selloff in January 2025. The V3.2 release in between introduced the sparse-attention line this architecture builds on but did not reset where DeepSeek ranked against competing open-weight labs the way V4 did.

Sources

  1. [1]
    DeepSeek V4 Preview Release

    DeepSeek · Apr 24, 2026

  2. [2]
  3. [3]
    deepseek-ai/DeepSeek-V4-Pro

    Hugging Face · Apr 24, 2026

  4. [4]