A few days ago, DeepSeek officially released the V4 preview, and this version really attracted a lot of attention. Rumors had been circulating since before the Chinese New Year. Since I happened to be leaving my job at the time, I didn’t get to try it out immediately. Now that I have some time, I integrated it with Opencode and Multica and wrote this blog post to test it out.
From late 2022 to early 2023, ChatGPT exploded in popularity, and I started using LLMs to assist with script writing. Although it was quite useful, the price was relatively high, and payment was always an issue, so its application was limited to simple coding problems.
From late 2024 to early 2025, DeepSeek became a hit. While its answers often weren’t entirely satisfactory, and the addition of a “thinking mode” made the response time a bit slower, it was really cheap! A year later, DeepSeek remains one of the most affordable models in terms of tokens while still delivering decent output. I paid 50 RMB at the beginning of the last year, and now, almost exactly a year later, I still have 27 RMB left… As a result, I’ve become much bolder in applying LLMs to various other areas.