Tasks and inputs
PaddleOCR VL is listed for Document OCR. It accepts text, image and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
PaddleOCR VL from paddlepaddle: Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts. The registry places it in the paddlepaddle catalog with a release date of 2025-10-16. This profile describes its documented interface and how to evaluate it for the intended task.
The recorded inputs are text and image, with text output. The registry lists a 131,072-token context window and up to 16,384 output tokens. Additional capability flags are not established by this record. These are specifications, not a measured quality or speed ranking. A host can impose its own request limits and support a different subset of features.
The registry marks PaddleOCR VL as an open-weight model. Check the linked checkpoint’s licence and runtime requirements before downloading or deploying it. Open weights describe availability, while licence terms determine permitted use. Local inference still requires hardware; a hosted route can charge separately.
No independently checked token rate is added from a hosting alias. Use the route’s current price and billing unit when comparing cost, including output, reasoning, cache behavior and retries where applicable.
Start with representative prompts and an agreed acceptance rubric. Include missing information, contradictory evidence and outputs that must follow a schema. Compare accepted results, complete request cost and response time under the same deployment conditions.
A supporting source document was retrieved for this entry. Specifications above remain attributed to the models.dev record unless the publisher supplies a more specific limit. SyncDev has not independently benchmarked PaddleOCR VL.
Browse paddlepaddle models, explore related tasks, or compare two models using the same workload.
The registry lists Novita AI with model ID paddlepaddle/paddleocr-vl. This identifies that host's route, rather than establishing a first-party publisher API ID. Check its current access, request limits and billing before integration.
Compare the model on the work you need to complete.
PaddleOCR VL is listed for Document OCR. It accepts text, image and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 131.07K context and 16.38K maximum output. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
The weights are downloadable under Apache-2.0. Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Mistral AI
Mistral OCR 4.1 is a document-processing service for extracting text, structure and layout information from supplied pages.
deepseek-ai
Hugging Face repository for Image-text-to-text.
Tencent
WeVisDoc 2B converts document-page images into structured text, including formulas and tables.
Tencent
WeVisDoc 4B converts document-page images into structured text, including formulas and tables.