Mistral AI · Schema

OcrRequest

AgentsArtificial IntelligenceBatch ProcessingChatEmbeddingsFine-TuningLarge Language ModelsOCR

Properties

Name Type Description
model string ID of the model to use for OCR processing.
document object
pages array Specific page numbers to process. If not provided, all pages are processed.
include_image_base64 boolean Whether to include base64-encoded images of extracted figures and charts in the response.
image_limit integer Maximum number of images to extract and return.
image_min_size integer Minimum size in pixels for images to be included in the response.
View JSON Schema on GitHub

JSON Schema

mistral-ai-ocrrequest-schema.json Raw ↑ 
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/OcrRequest",
  "title": "OcrRequest",
  "type": "object",
  "required": [
    "model",
    "document"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "ID of the model to use for OCR processing.",
      "example": "mistral-ocr-latest"
    },
    "document": {
      "$ref": "#/components/schemas/DocumentInput"
    },
    "pages": {
      "type": "array",
      "description": "Specific page numbers to process. If not provided, all pages are processed.",
      "items": {
        "type": "integer",
        "minimum": 0
      }
    },
    "include_image_base64": {
      "type": "boolean",
      "description": "Whether to include base64-encoded images of extracted figures and charts in the response.",
      "default": false
    },
    "image_limit": {
      "type": "integer",
      "description": "Maximum number of images to extract and return.",
      "minimum": 0
    },
    "image_min_size": {
      "type": "integer",
      "description": "Minimum size in pixels for images to be included in the response.",
      "minimum": 0
    }
  }
}