—per task?
self-host onlyprice
—output speed?
131Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
XOpenTeleOCRsame——Context: 131K → 128K+1AOpenOvisOCR2same—$0.30 / $1.20POpenPaddleOCR VL 1.5-1%——ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
Nothing here yet.
Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
History
2 versionsBenchmarks
in Vision & DocumentsOmniDocBench · v1.6 · full96.3#3
FAQ
How much does PaddleOCR VL 1.6 cost?›
There is no per-unit API price: self-host only.
Is PaddleOCR VL 1.6 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is PaddleOCR VL 1.6, and what is it best at?›
#3 of 22 in Vision & Documents.
Is PaddleOCR VL 1.6 better than OvisOCR2?›
On OmniDocBench · v1.6 · full, PaddleOCR VL 1.6 scores 96.3 vs 96.5 — about the same.
What is the context window of PaddleOCR VL 1.6?›
131K tokens.
When was PaddleOCR VL 1.6 released? Is there a newer version?›
Released 2026-05-27. It is the current version in its line.
Is PaddleOCR VL 1.6 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run PaddleOCR VL 1.6 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can PaddleOCR VL 1.6 read images?›
It accepts text and images as input.
What is PaddleOCR VL 1.6?›
PaddleOCR VL 1.6 is an open-weights language model from PaddlePaddle, released May 2026.
What are the best alternatives to PaddleOCR VL 1.6?›
TeleOCR (open weights).