DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. $0.435 per million input tokens, $0.87 per million output tokens. 1,048,576 token context window, maximum output of 384,000 tokens.
1027 points by explosion-s 70 days ago openrouter.ai 445 comments

Summary

DeepSeek V4 Pro 0813 introduces a powerful mixture-of-experts model designed for handling extensive input and output token requirements, making it suitable for complex tasks. With a massive context window and high output capacity, it aims to enhance efficiency in processing large datasets.

Comments (445 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open