—per task?
self-host onlyprice
—output speed?
164Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5.1unstated+7%—$1.25 / $10iOpenIntern S1-3%——Context: 164K → 66KBettero3unstated+3%—$2 / $8
OpenSkywork R1V3 38B-5%——Context: 164K → 33KOpenSkywork R1V2 38B-8%——Context: 164K → 41KModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
iIntern S1Open-3%——Context: 164K → 66KSkywork R1V3 38BOpen-5%——Context: 164K → 33KSkywork R1V2 38BOpen-8%——Context: 164K → 41K
Llama 4 MaverickunstatedOpen-8%—$0.19 / $0.65
QVQ 72B PreviewOpen-12%—$0.25 / $0.50Context: 164K → 32KModelScoreCostPer taskWhat changes
dDots.ocrOpenn/a——Context: 164K → 131KdDots3-Note Previewn/a——All dots-studio models →Run it yourself
Fits onhardware needs not verified yet
LicenceMITfree for commercial use
Benchmarks
in Vision & DocumentsMMMU · validation80.1#4
FAQ
How much does Dots.vlm1.inst cost?›
There is no per-unit API price: self-host only.
Is Dots.vlm1.inst free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Dots.vlm1.inst, and what is it best at?›
#4 of 41 in Vision & Documents.
Is Dots.vlm1.inst better than Claude Opus 4.5?›
On MMMU · validation, Dots.vlm1.inst scores 80.1 vs 80.7 — about the same.
What is the context window of Dots.vlm1.inst?›
164K tokens.
When was Dots.vlm1.inst released? Is there a newer version?›
Released 2025-08-05. It is the current version in its line.
Is Dots.vlm1.inst open source?›
Yes, the weights are open (MIT licence).
Can I run Dots.vlm1.inst locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Dots.vlm1.inst read images?›
It accepts text and images as input.
What is Dots.vlm1.inst?›
Dots.vlm1.inst is an open-weights language model from dots-studio, released Aug 2025.
What are the best alternatives to Dots.vlm1.inst?›
GPT-5.1 (better), Intern S1 (open weights).