Mathpix · Schema

Mathpix Image OCR Result

Schema for the response returned by POST /v3/text. Covers Mathpix Markdown plus optional styled LaTeX, HTML, structured data, line- and word-level segmentation, and confidence metrics.

OCRSTEMMathChemistryDocument ConversionPDFLaTeXHandwritingArtificial IntelligenceMachine-Learning

Properties

Name Type Description
request_id string Unique identifier for debugging.
text string Recognized content in Mathpix Markdown.
latex_styled string Styled LaTeX equivalent of the recognized math.
html string HTML rendering of the recognized content.
data array Structured data extracted from the image (tables, equations).
confidence number Probability of 100% accuracy in the range 0.0 - 1.0.
confidence_rate number Output quality confidence in the range 0.0 - 1.0.
is_printed boolean
is_handwritten boolean
auto_rotate_confidence number
auto_rotate_degrees integer
image_height integer
image_width integer
line_data array Per-line segmentation when include_line_data=true.
word_data array Per-word segmentation when include_word_data=true.
version string
error string
View JSON Schema on GitHub

JSON Schema

mathpix-image-result-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://api-evangelist.com/schemas/mathpix/mathpix-image-result-schema.json",
  "title": "Mathpix Image OCR Result",
  "description": "Schema for the response returned by POST /v3/text. Covers Mathpix Markdown plus optional styled LaTeX, HTML, structured data, line- and word-level segmentation, and confidence metrics.",
  "type": "object",
  "properties": {
    "request_id": {
      "type": "string",
      "description": "Unique identifier for debugging."
    },
    "text": {
      "type": "string",
      "description": "Recognized content in Mathpix Markdown."
    },
    "latex_styled": {
      "type": "string",
      "description": "Styled LaTeX equivalent of the recognized math."
    },
    "html": {
      "type": "string",
      "description": "HTML rendering of the recognized content."
    },
    "data": {
      "type": "array",
      "description": "Structured data extracted from the image (tables, equations).",
      "items": {
        "type": "object",
        "properties": {
          "type": {"type": "string"},
          "value": {"type": "string"}
        },
        "additionalProperties": true
      }
    },
    "confidence": {
      "type": "number",
      "description": "Probability of 100% accuracy in the range 0.0 - 1.0.",
      "minimum": 0,
      "maximum": 1
    },
    "confidence_rate": {
      "type": "number",
      "description": "Output quality confidence in the range 0.0 - 1.0.",
      "minimum": 0,
      "maximum": 1
    },
    "is_printed": {"type": "boolean"},
    "is_handwritten": {"type": "boolean"},
    "auto_rotate_confidence": {"type": "number"},
    "auto_rotate_degrees": {
      "type": "integer",
      "enum": [0, 90, -90, 180]
    },
    "image_height": {"type": "integer"},
    "image_width": {"type": "integer"},
    "line_data": {
      "type": "array",
      "description": "Per-line segmentation when include_line_data=true.",
      "items": {
        "type": "object",
        "properties": {
          "type": {"type": "string"},
          "subtype": {"type": "string"},
          "cnt": {
            "type": "array",
            "items": {"type": "array", "items": {"type": "number"}}
          },
          "included": {"type": "boolean"},
          "is_printed": {"type": "boolean"},
          "is_handwritten": {"type": "boolean"},
          "text": {"type": "string"}
        },
        "additionalProperties": true
      }
    },
    "word_data": {
      "type": "array",
      "description": "Per-word segmentation when include_word_data=true.",
      "items": {"type": "object", "additionalProperties": true}
    },
    "version": {"type": "string"},
    "error": {"type": "string"}
  },
  "additionalProperties": false
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/mathpix-image-result"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.