Model Releases
DeepSeek-V4: a million-token context that agents can actually use
DeepSeek-V4 is an advanced language model featuring a million-token context window that enables practical agentic applications beyond simple retrieval. The model demonstrates improved efficiency and u
DeepSeek-V4 is an advanced language model featuring a million-token context window that enables practical agentic applications beyond simple retrieval. The model demonstrates improved efficiency and usability for long-context tasks, addressing previous limitations where extremely long contexts were theoretically supported but difficult to leverage effectively in real-world agent scenarios.
Related
- Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs
- also available on the Claude Blog: https://claude.com/blog/using-claude-code-session-management-and-1m-context
- Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations
- also now available on the Claude Blog: https://claude.com/blog/using-claude-code-session-management-and-1m-context
- The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break
- DeepSeek V4 Pro has 1.6T total parameters, its largest model by the metric, and V4 Flash has 284B parameters; both models have a context window of 1M tokens (Vincent Chow/South China Morning Post)
Source: Hugging Face | 2026-04-24