csviverdeia/deepseek-ocr-2

DeepSeek-OCR 2 (3.4B) - OCR multilíngue com extração estruturada de documentos (markdown)

Public
11 runs

Run csviverdeia/deepseek-ocr-2 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
image
string
Imagem com texto (.jpg/.png/.webp) para extrair OCR.
mode
None
markdown
Modo de extração.
custom_prompt
string
(Apenas se mode=custom) Prompt customizado. Deve começar com '<image>\n'.
base_size
integer
1024

Min: 512

Max: 2048

Resolução base (recomendado 1024).
image_size
integer
768

Min: 512

Max: 1536

Resolução de crop (recomendado 768).
crop_mode
boolean
True
Ativa modo crop dinâmico (mais preciso em documentos grandes).

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "string",
  "title": "Output"
}