I wonder if/when the US limits market entry of Deepseek and other Chinese model vendors like they have done with Huawei
How would that be technically feasible? Would we get IP bans?
DeepSeek makes the V4 Pro price discount permanent
91–100 of 586 posts
Re: DeepSeek makes the V4 Pro price discount permanent
#92Once they have their own coding agent which they seem to be working towards, I may start predominantly using their models. They seem to be doing all the "right" things, open sourcing models, publishing research, and keeping prices low for everyone.
antirez's ds4-agent works quite fine. It runs on any Apple Silicon device with 96GB RAM or more.
I wonder how many years it'll take for the API token cost to exceed the money spent on ram.
Re: DeepSeek makes the V4 Pro price discount permanent
#93Once they have their own coding agent which they seem to be working towards, I may start predominantly using their models. They seem to be doing all the "right" things, open sourcing models, publishing research, and keeping prices low for everyone.
Both pi, opencode and zed work amazing with deepseek.
Re: DeepSeek makes the V4 Pro price discount permanent
#94Earlier quoted context omitted.
Why do you need them to provide a coding agent? Just use their model with any off the shelf coding agent. I happen to prefer Pi, but use whatever works for you.
What's the best way to use it with Pi, OpenRouter?
I only use local models myself personally. But yeah, OpenRouter would probably be a good option.
Re: DeepSeek makes the V4 Pro price discount permanent
#95I am more worried about accidental data leak (agent reading env file for example) with the Chinese hosted models compared to the US hosted models. Am I wrong to suspect that the Chinese government might be more likely to scan all chats and save useful information compared to the US government or company? I hesitated to even post this comment as it sounds biased and xenophobic. I would love for someone to convince me…
Just use it through something like Azure. They host the entire model and serve it from the US. I'm sure that there are other providers like this. We use it that way and it works great.
You don't get the cheap pricing this way, which is why people are so interested in the model in the first place.
Re: DeepSeek makes the V4 Pro price discount permanent
#96That is some insane value. I've been using GLM Coding Plan Max with GLM 5.1 for a while and i've tested DeepSeek V4 Pro maybe for 3 weeks now and I found it to be better than GLM 5.1 for complex coding tasks. I've used 65m tokens and with that price it cost me $1.5, that's really cheap.
I think Deepseek uses much more tokens than other models.
But way less dollars. Which is the important metric.
Re: DeepSeek makes the V4 Pro price discount permanent
#97Earlier quoted context omitted.
Why do you need them to provide a coding agent? Just use their model with any off the shelf coding agent. I happen to prefer Pi, but use whatever works for you.
What's the best way to use it with Pi, OpenRouter?
> What's the best way to use it with Pi, OpenRouter?
I can't claim it's "the best"...
But the Pi.dev and OpenRouter combo is what I'm doing at home, and I love it. Setup was easy, I can use /model to switch between any of the openrouter models and whatever I'm hosting locally via VLLM.
Re: DeepSeek makes the V4 Pro price discount permanent
#98Once they have their own coding agent which they seem to be working towards, I may start predominantly using their models. They seem to be doing all the "right" things, open sourcing models, publishing research, and keeping prices low for everyone.
Earlier this week I started testing Chinese models on my codebase. I haven’t really looked at interactive coding yet, but more at issue triage, bug auto-fixing, log analytics, etc.
I used DeepSeek, Kimi, GLM, Qwen, and MiMO against GPT-5.5 high as reference, all running in Pi harness without anything installed.
So far, Kimi and MiMO look the most promising to me. I haven’t tested them rigorously enough to make a strong statement, but my first impression is that, in practice, all those models may be less behind on typical daily tasks than people think.
They are a bit “work hard, not smart". Getting to same-ish results more slowly and using more tokens, but at a fraction of the price
Re: DeepSeek makes the V4 Pro price discount permanent
#99Earlier quoted context omitted.
They’re playing games behind the scenes to massage and manage their earnings. China is gonna win long term there’s no doubt. The fact that the American firms haven’t created immense escape velocity despite the disparity in spending is quite telling.
The nice thing about hosting inference locally is that you can be sure you're not being rug-pulled in any way. This doesn't really help China 'win' though, it's just freeloading on them making their weights openly available.
The good thing is, we're only 2.5 years away from a top of the line MacBook having better local inference than CC Opus does today.
That's more than good enough if you're actually getting what CC Opus is capable of.
I've never been so excited for the future.
Re: DeepSeek makes the V4 Pro price discount permanent
#100Earlier quoted context omitted.
You can use V4 Pro with Claude Code [1]. I tried it and it's impressive. [1]: https://api-docs.deepseek.com/quick_start/agent_integrations...
I am curious - Is there a way to switch between models depending on the task? Because I believe Deepseek V4 is not multimodal and it will be good to switch back to Claude if vision or other capabilities are required.
I was looking into something similar because I wanted to test a local model for doing basic coding and smart model (deepseek) for planning.
It's basically not possible with claude code, the api endpoint is a single environment variable and whatever models are on that endpoint are what's available.
HOWEVER, if you run a proxy like LiteLLM, you can configure it to send requests to different api endpoints on the back end and expose them as different "models" on the front end, then configure claude code to switch between those virtual models.