Baidu · Paddleocr VL 1 5 · active
PaddleOCR-VL-1.5
PaddleOCR-VL-1.5 is an open-weight vision-language model published by Baidu.
PaddlePaddle/PaddleOCR-VL-1.5This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Provider availability
Serving endpoints and pricing
Technical specification
Capabilities
Version lineage
Explicit unknowns
- Maximum output
- Knowledge cutoff
- API availability
- Provider pricing
Comparable peers
Related model comparisons
Questions
PaddleOCR-VL-1.5 FAQs
What is PaddleOCR-VL-1.5?+
PaddleOCR-VL-1.5 is an open-weight vision-language model published by Baidu. It is developed by Baidu and its current sourced lifecycle status is active.
What inputs and outputs does PaddleOCR-VL-1.5 support?+
PaddleOCR-VL-1.5's current record lists Text and Image as input and Text as output.
How much context does PaddleOCR-VL-1.5 support?+
The current record lists a 131,072-token context window and does not report a maximum output length.
Is PaddleOCR-VL-1.5 available through an API?+
PaddleOCR-VL-1.5's current primary-source record does not establish API availability. No provider endpoint is treated as available without direct provider evidence.
How large is PaddleOCR-VL-1.5?+
The current record lists 958.6M total parameters and an unknown active parameter count. Its architecture is PaddleOCRVLForConditionalGeneration.
What capabilities and tasks does PaddleOCR-VL-1.5 support?+
PaddleOCR-VL-1.5's recorded capabilities are chat and generation. Its supported tasks are image and text.
Can PaddleOCR-VL-1.5 be self-hosted?+
PaddleOCR-VL-1.5 is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does PaddleOCR-VL-1.5 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are PaddlePaddle/PaddleOCR-VL-1.5.
Which models can PaddleOCR-VL-1.5 be compared with?+
The current compatible peer set includes GLM-OCR, granite-vision-4.1-4b, Ministral-3-3B-Instruct-2512, Ministral-3-8B-Instruct-2512, and Molmo2-8B. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
How current is the Model Markets record for PaddleOCR-VL-1.5?+
PaddleOCR-VL-1.5 was last verified Aug 28, 2026 from Baidu's primary source, “PaddlePaddle/PaddleOCR-VL-1.5 developer model repository.” The evidence is classified as official fact.
Primary evidence