DS being unable to precisely view Playwright screenshots is the only thing I really miss from Sonnet. This is promising.
> Images are converted into tokens based on their dimensions, and these tokens are billed together with your text tokens.
> Before inference, every image is automatically resized:
> - Images with a total pixel count below roughly 384×384 are scaled up while preserving their aspect ratio.
> - Larger images are scaled down while preserving their aspect ratio so that the total pixel count after resizing is roughly that of an 800×800 image.
> As a result, there is an upper bound of 384 tokens per image: for example, a 2000×2000 image and a 5000×5000 image consume the same number of tokens after resizing. When a request contains multiple images, each image is counted independently under the same rule—there is no separate calculation for multi-image requests.
400 tokens per image results in 2,500 images per dollar, if I’m not mistaken.
For most use cases you can fix that in the harness. Just give the model a tool to request a crop of specific coordinates of any image it has in its context. Call the tool "zoom" and it should be intuitive for the model
Maybe there are some use cases where you need high detail everywhere at once, but for OCR of small text and the like a zoom ability should be sufficient
Might still be fine. The most recent crop of vLLMs proactively use whichever programs are available on the system (e.g. ImageMagick or PIL) to "zoom in" by cropping subimages if they can't quite make out the details.
800x800 is 640,000 pixels, or 0.64 Megapixels. That is less than the resolution of computer screens from 1995, Super VGA which has around 0.79 MPs.
This is useful for a reasonable amount of use-cases, but I think the watershed rez will be around triple that, ~1080p, which is enough for almost anything, except small text and subtle details.
Interesting. Wasn't Deepseek's founder saying that they had explicitly decided not to focus on multimodal models at all and were going text-only because they believed it was enough to achieve AGI?
I've heard that DeepSeek v4 Flash 0731 has frequently assumed that it has vision capabilities and then resorts to inventing text-based image analysis tools when it finds that it actually can't see. In that case, this is a great upgrade for the model.
Anecdotally, I had to tell 0731 to refrain from viewing screenshots since it kept breaking its sessions by trying to read images.
DS being unable to precisely view Playwright screenshots is the only thing I really miss from Sonnet. This is promising.
> Images are converted into tokens based on their dimensions, and these tokens are billed together with your text tokens.
> Before inference, every image is automatically resized:
> - Images with a total pixel count below roughly 384×384 are scaled up while preserving their aspect ratio.
> - Larger images are scaled down while preserving their aspect ratio so that the total pixel count after resizing is roughly that of an 800×800 image.
> As a result, there is an upper bound of 384 tokens per image: for example, a 2000×2000 image and a 5000×5000 image consume the same number of tokens after resizing. When a request contains multiple images, each image is counted independently under the same rule—there is no separate calculation for multi-image requests.
400 tokens per image results in 2,500 images per dollar, if I’m not mistaken.
edit: format.
Oof 800 by 800 kills a lot of use cases
For most use cases you can fix that in the harness. Just give the model a tool to request a crop of specific coordinates of any image it has in its context. Call the tool "zoom" and it should be intuitive for the model
Maybe there are some use cases where you need high detail everywhere at once, but for OCR of small text and the like a zoom ability should be sufficient
Might still be fine. The most recent crop of vLLMs proactively use whichever programs are available on the system (e.g. ImageMagick or PIL) to "zoom in" by cropping subimages if they can't quite make out the details.
flash vs fine details. Pick one.
Gemini "flash" models have an option for media resolution, including a high resolution option for screenshots.
Congratulations! DeepSeek has finally gained eyes — the dark days are about to be behind us.
800x800 is 640,000 pixels, or 0.64 Megapixels. That is less than the resolution of computer screens from 1995, Super VGA which has around 0.79 MPs.
This is useful for a reasonable amount of use-cases, but I think the watershed rez will be around triple that, ~1080p, which is enough for almost anything, except small text and subtle details.
You'd expect a tool-enabled model to leverage crop and zoom tools to inspect and validate what it thinks it's seeing, though.
> Larger images are scaled down while preserving their aspect ratio, so that the total pixel count after resizing is roughly that of an 800×800 image.
It's useful but for OCR and a lot of other applications it needs to be a bit higher (eg: putting in a full A4 / Letter sized page)
Can split and feed?
that's difficult as well, how do you k ow where to split?
Interesting. Wasn't Deepseek's founder saying that they had explicitly decided not to focus on multimodal models at all and were going text-only because they believed it was enough to achieve AGI?
I've heard that DeepSeek v4 Flash 0731 has frequently assumed that it has vision capabilities and then resorts to inventing text-based image analysis tools when it finds that it actually can't see. In that case, this is a great upgrade for the model.
Anecdotally, I had to tell 0731 to refrain from viewing screenshots since it kept breaking its sessions by trying to read images.
will this be open weights?