DeepSeekDeepSeek·text

DeepSeek V4 Flash

CodeReasoningWeb searchFunction calling
Quick reference
DeepSeek V4 Flash — TLDR
  • 🆕 Efficiency-optimized member of DeepSeek's V4 preview series, released April 2026.
  • 🧠 284B-parameter Mixture-of-Experts with only 13B active per token.
  • 📏 One-million-token context window, now DeepSeek's default standard.
  • 🔧 Hybrid attention pairs Compressed Sparse and Heavily Compressed Attention.
  • ⚡ Tuned for fast, high-throughput, cost-efficient inference.
  • 💬 Dual Thinking and Non-Thinking modes via one model.
  • 🎯 Capable in reasoning, coding, function-calling, and agentic tool use.
  • 🔒 Released under the permissive MIT license.
💰 Best price on AntSeed
FREE / FREE
per 1M · cheapest in / out
📏 Context
1M tokens
🐜 Sellers
22
advertising on AntSeed
Provider

DeepSeek is a Chinese artificial intelligence company specializing in large language model development, founded in July 2023 by Liang Wenfeng. Based in Hangzhou, Zhejiang, the company is backed by High-Flyer, a prominent Chinese hedge fund also co-founded by Liang. DeepSeek…

Explore 3 more models by DeepSeek
About this model

DeepSeek V4 Flash is the lightweight half of DeepSeek's V4 preview series, launched alongside [[sibling:deepseek-v4-pro|DeepSeek V4 Pro]] on April 24, 2026. Where the Pro model carries 1.6 trillion total parameters with 49 billion active, Flash uses a much smaller 284-billion-parameter Mixture-of-Experts design activating just 13 billion parameters per token — positioning it as DeepSeek's economical, high-throughput option. Both models share a one-million-token context window, which the company states is now the default across its services.

The V4 family introduces a new hybrid attention mechanism combining Compressed Sparse Attention and Heavily Compressed Attention, plus DeepSeek Sparse Attention, to cut long-context compute and memory cost. DeepSeek reports that, at the 1M-token setting, the Pro variant needs only 27% of single-token inference FLOPs and 10% of the KV cache compared with the prior-generation [[sibling:deepseek-v3.2|DeepSeek V3.2]], illustrating the architectural efficiency gains this generation targets.

Both V4 models support Thinking and Non-Thinking modes and an OpenAI- and Anthropic-compatible API. DeepSeek notes that Flash's maximum-effort mode can reach reasoning quality comparable to Pro when given a larger thinking budget, though its smaller scale leaves it slightly behind on pure-knowledge tasks and the most complex agentic workflows.

The model targets advanced reasoning, software engineering, tool use, and enterprise assistants, and ships under the MIT license.

View source on GitHub ↗View model card on HuggingFace ↗
Sources
api-docs.deepseek.comDeepSeek V4 Preview Release | DeepSeek API Docs· api-docs.deepseek.combuild.nvidia.comdeepseek-v4-flash Model by Deepseek-ai· build.nvidia.comhuggingface.codeepseek-ai/DeepSeek-V4-Flash · Hugging Face· huggingface.co

This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.

Sellers serving DeepSeek V4 Flash (22)
SellerReputationInput $/MCached $/MOutput $/MCategoriesAPI

"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens, not settled amounts). Reputation = on-chain trust (0-100). Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase.