←back to thread

DeepSeek-v3.1

(api-docs.deepseek.com)
776 points wertyk | 5 comments | 21 Aug 25 19:06 UTC | HN request time: 0.904s | source
Show context
esafak ◴[21 Aug 25 20:12 UTC] No.44977474[source]▶
It seems behind Qwen3 235B 2507 Reasoning (which I like) and gpt-oss-120B: https://artificialanalysis.ai/models/deepseek-v3-1-reasoning

Pricing: https://openrouter.ai/deepseek/deepseek-chat-v3.1

replies(2): >>44977550 #>>44981531 #
bigyabai ◴[21 Aug 25 20:18 UTC] No.44977550[source]▶
Those Qwen3 2507 models are the local creme-de-la-creme right now. If you've got any sort of GPU and ~32gb of RAM to play with, the A3B one is great for pair-programming tasks.
replies(4): >>44977707 #>>44978006 #>>44978062 #>>44979710 #
1. indigodaddy ◴[22 Aug 25 00:08 UTC] No.44979710[source]▶
Do we get these good qwen models when using qwen-code CLI tool and authing via qwen.ai account?
replies(2): >>44987679 #>>44989538 #
2. bigyabai ◴[22 Aug 25 18:05 UTC] No.44987679[source]▶
I'm not sure, probably?
3. esafak ◴[22 Aug 25 20:39 UTC] No.44989538[source]▶
You do not need qwen-code or qwen.ai to use them; openrouter + opencode suffice.
replies(1): >>44989707 #
4. indigodaddy ◴[22 Aug 25 20:56 UTC] No.44989707[source]▶
Right, I'm aware, was just wondering about that specific scenario.
replies(1): >>44989881 #
5. esafak ◴[22 Aug 25 21:13 UTC] No.44989881{3}[source]▶
I don't know about qwen.ai but you can use that model in qwen-cli through openrouter or Alibaba Cloud ModelStudio: https://www.alibabacloud.com/help/en/model-studio/models#42e...