Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

news.ycombinator.com

Post reply on HN
Print view View original

121–130 of 221 posts

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#121

Post by bitexploder »

pimeys wrote: post #37
EbNar wrote: post #15

Since a few months, I almost exclusively use the Chinese "flash" models for my needs. They are a joy and they cost pennies per answer. Great job.

Yes. I'm working in the agent industry and my god are we excited on new versions of Chinese flash models. The direct competition is Gemini Flash, and these models are much better on agentic tasks with fraction of the task price compared to Gemini. Things like oh here's a set of simple instructions for you to follow, call these tools, return this report. 20-30% of the price per task. And especially Deepseek Flash prod…

Which versions of flash and at what thinking levels? Which chinese flash models and at what thinking levels? What tasks? What completion rates? How was quality evaluated?

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#123

Post by Xunjin »

weird-eye-issue wrote: post #113
weego wrote: post #106

Earlier quoted context omitted.

You absolutely cannot consider an LLM production build number something to be pinned against as a static dependency in a product chain, so it's a non-issue.

It's very easy to tell who is not running production applications using these models based on comments like this

Let me give you the benefit of the doubt, can you expand what you run in production?

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#124

Post by atwrk »

HansHamster wrote: post #36
calgoo wrote: post #17

Earlier quoted context omitted.

v4 flash has been working quite well for the majority of my personal projects, with occasional v4 pro or Kimi 3 for the most complicated tasks or to check the overall project progress (when vibe coding).

I must be doing something wrong. I gave v4 pro a try a couple of days ago, gave it a simple prompt like "clean up functions x and y in file z" and it would always start off promising, just to quickly get sidetracked, start hallucinating problems in the code, and just get stuck for hours until I interrupt it: — hmm — 0x2D696370 — little-endian bytes: 70 63 69 2D = 'p','c','i','-' — hmm — WAIT — WAIT — !!!!! — *WAIT —…

I guess this was a heavily quantized version from openrouter? I've never had that experience in the last months of quite intensive use of the official deepseek api.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#125

Post by bitexploder »

a-ve wrote: post #45

I've been using deepseek-v4-flash as a "worker" model with Claude Code to implement a tool using Rust/Iroh for my personal use, and it works fairly nicely when I use Opus as the planner/reviewer model. It seems to follow the plan generated by Opus, albeit with a few misses here and there that it cleans up later after being reviewed by Opus. Fairly excited for the v4.1 launch. Input cache hit prices have been halved,…

If you are okay with waiting use GLM 5.3 max. It costs more but still cheap. It is slow, but a very strong worker. Still dollars per day (at most) with heavy concurrent agent running. I load up planning and tasks in Opus or Sol, and just have glm flash workers go to town every night. My project has never advanced more smoothly.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#126

Post by gentlewater »

elaus wrote: post #107
gentlewater wrote: post #92

Earlier quoted context omitted.

I finally uninstalled the app yesterday after giving it plenty of chances over several months. Yesterday, I asked it whether «DeepSeek has fixed the issue where it erroneously answers in Chinese?» and it answered in Chinese.

So you did not do what the post you replied to suggested?

Oh, I’ve tried that too. It will promise to keep it in English from here on out, then switch back to Chinese after two or three exchanges. When ever it needs to do a web search, it seems to load so much Chinese text that it forgets any language instructions. Just thought my experience yesterday was more to the point. Right now the chat is absolutely hopeless.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#127

Post by pimeys »

bitexploder wrote: post #121
pimeys wrote: post #37

Earlier quoted context omitted.

Yes. I'm working in the agent industry and my god are we excited on new versions of Chinese flash models. The direct competition is Gemini Flash, and these models are much better on agentic tasks with fraction of the task price compared to Gemini. Things like oh here's a set of simple instructions for you to follow, call these tools, return this report. 20-30% of the price per task. And especially Deepseek Flash prod…

Which versions of flash and at what thinking levels? Which chinese flash models and at what thinking levels? What tasks? What completion rates? How was quality evaluated?

- Which versions: 3.6 vs 3.7 vs. 3.8 for Gemini Flash, and v4 0731 for Deepseek v4 Flash, and GLM 5.3 Flash

- Medium for Gemini, high for Deepseek.

- Things like find information, then understand something about it, then send a slack message or email etc.

- Completion rates somewhere in 80-90%, Deepseek a bit better than Gemini

- Quality evaluated by Fable 5.1 and Astra 6.0 acting as a rubric judge.

Gemini quality would probably be better with high thinking level, but that would be 40% more expensive. And Deepseek is already third the price of Gemini.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#128

Post by alightsoul »

michimagdesign wrote: post #117
elaus wrote: post #107

Earlier quoted context omitted.

So you did not do what the post you replied to suggested?

This shouldn’t be a user-facing issue. The web UI should inject the account’s language setting or solve it like competitors. They’ve mentioned giving it multiple chances but it’s still not fixed.

Anthropic does the same thing but it's not problem

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#129

Post by Xiol32 »

m00dy wrote: post #91
ricardobeat wrote: post #24

Earlier quoted context omitted.

These models are open-weights. Anyone can host them, you don’t have to use chinese servers even though most of them offer zero data-retention policies.

>>zero data-retention policies Yeah, that’s basically an industry-wide scam.

But it makes the compliance team happy.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#130

Post by samuelknight »

weego wrote: post #106
aftbit wrote: post #67

>In keeping with our commitment to user responsibility, following the official launch of V4.1 Flash and prior to the release of V4.1 Pro, all requests to the Pro model will be routed to V4.1 Flash and billed at Flash's price Please don't do this kind of thing. If a user has validated a workflow on V4 Pro, they might not want to suddenly start testing it in production on V4.1 Flash. Instead, keep V4 Pro around but dep…

You absolutely cannot consider an LLM production build number something to be pinned against as a static dependency in a product chain, so it's a non-issue.

Yes you can and you should. Providers have SLAs for when models roll off support and this has been the case for APIs long before LLMs. For example https://platform.claude.com/docs/en/about-claude/model-depre... and https://developers.openai.com/api/docs/deprecations
Post reply on HN