For those not trying, this allows Deepseek to understand a picture (instead of just extracting text from it), and it can describe what's in the picture, but this is not an image generation system, so you can't ask it to modify an image.
Personally, I'm a bit surprised the DS chat app still doesn't offer its own text to speech and speech to text features (I know DS doesn't have any ASR model for example, but there are quite a few in the open).
throwaw12 6 minutes ago [-]
I wish they published a post where we read about capabilities, quality, accuracy and other parameters
tornikeo 46 minutes ago [-]
I really need this as an API.
Turns out, to use Claude Agents SDK, you need to have a vision enabled API. If Deepseek API could see, it can fully drive Claude Code and Claude Agents SDK. A project I'm working on relies on a Claude-in-CloudflareWorker setup and I've been relying on Qwen and gemini flash lite, both more expensive than Deepseek.
What has been going on with deepseek recently? I have gotten lots of replies in Chinese and even more frequently, reasoning in Chinese as well.
Is it a new silent update?
serf 10 minutes ago [-]
This happens to me a lot when I ask a qwen3.6 model to respond to a question in JSON. No clue why.
Shank 1 hours ago [-]
Well, it is a Chinese model, maybe it thinks better in Chinese?
surgical_fire 13 minutes ago [-]
I use DeepSeek daily, never happened to me.
I use the API however, not the chat interface.
abyssin 1 hours ago [-]
It doesn’t seem that recent to me, at least been like that for six months.
RIshabh235 1 hours ago [-]
yes, kind of silent update plus they might have better chinese datasets and user data for their training, that might be leading to chinese preference.
alfiedotwtf 34 minutes ago [-]
Are you running out of context? I’ve found that tooling and giberish most of the time happens when I’m butting up against the high watermark of my context window. One other thing it could be, I’ve read that lower quanta like Q1 and Q2 for smaller models can leak Chinese
epolanski 55 minutes ago [-]
It never happened to me with Deepseek, but it happened multiple times with Kimi 2.6.
It also happened a handful of times with Anthropic models.
arjie 52 minutes ago [-]
If they'd do one of those little extraneous additions like Qwen does, so that I can have DS4 Flash with Vision that would be great. I've got to run a separate model entirely so that I can get vision and I'd prefer to just put it all in one space.
earth2mars 1 hours ago [-]
And it's really good and fast. Have tested with bunch of odd photos on what is happening. Overall the training set seems large enough to know what's what and where
RIshabh235 1 hours ago [-]
yes and I hope their rate of shipping increases after recent funding.
crvdgc 1 hours ago [-]
Vision has been in A/B testing for a while now (at least in China). Is there an official announcement that this will be available for everyone?
RIshabh235 1 hours ago [-]
I haven't seen any official announcement yet, works for me though.
innis226 1 hours ago [-]
Nice, is this available in the API now as well?
naseemali925 58 minutes ago [-]
I am also waiting on the vision support in API. Its the only thing blocking me from buying their subscription.
dakolli 14 minutes ago [-]
What subscription?
RIshabh235 1 hours ago [-]
Not in the api yet.
2 hours ago [-]
hklohani 47 minutes ago [-]
[flagged]
ValveFan6666 1 hours ago [-]
[dead]
1 hours ago [-]
andrewstuart 1 hours ago [-]
OpenAI and Anthropic need to get this free foreign competition banned.
epolanski 54 minutes ago [-]
Care to expand on why? Or did you forgot the /s at the end?
dudisubekti 44 minutes ago [-]
I feel like '/s' has ruined irony on the internet. Irony is at its best if left ambiguous, lol.
cromka 11 minutes ago [-]
Nah, they're serious actually!
Weryj 32 minutes ago [-]
Wait, did that need a /s?
ReptileMan 26 minutes ago [-]
If everything goes to plan everyone involved with big US models will be trillionaire and everyone else will poor and unemployed. If there are open and cheap to run Chinese models (and please god silicon) the financial house of cards that we have build will fall, people involved with big US models will be poor and unemployed, and everyone else will be slightly less poor and unemployed than in the first scenario.
What is good for Dario is good for America.
andrewstuart 15 minutes ago [-]
Why do you think it’s free?
Any ideas, theories where they get their payoff?
cromka 11 minutes ago [-]
Yes, subscription options they sell on deepseek.com
Rendered at 08:13:15 GMT+0000 (Coordinated Universal Time) with Vercel.
Personally, I'm a bit surprised the DS chat app still doesn't offer its own text to speech and speech to text features (I know DS doesn't have any ASR model for example, but there are quite a few in the open).
Turns out, to use Claude Agents SDK, you need to have a vision enabled API. If Deepseek API could see, it can fully drive Claude Code and Claude Agents SDK. A project I'm working on relies on a Claude-in-CloudflareWorker setup and I've been relying on Qwen and gemini flash lite, both more expensive than Deepseek.
Can't wait to have it available on deepseek.
Is it a new silent update?
I use the API however, not the chat interface.
It also happened a handful of times with Anthropic models.
What is good for Dario is good for America.
Any ideas, theories where they get their payoff?