Process Equations (deprecated)

warning

Deprecated — use v3/text instead.

Legacy endpoint for processing equation images. Returns recognized LaTeX in multiple output formats.

POST v3/latex

POST api.mathpix.com/v3/latex

Process a single equation image and return recognized LaTeX in multiple output formats. Accepts an image URL or file upload. Use v3/text instead for new integrations.

Example

cURL

curl -X POST https://api.mathpix.com/v3/latex \
-H 'app_id: APP_ID' \
-H 'app_key: APP_KEY' \
-H 'Content-Type: application/json' \
--data '{"src": "https://cdn.mathpix.com/examples/equation.jpg", "formats": ["latex_simplified", "text"]}'

Python

import requests
r = requests.post("https://api.mathpix.com/v3/latex",
    json={
        "src": "https://cdn.mathpix.com/examples/equation.jpg",
        "formats": ["latex_simplified", "text"]
    },
    headers={
        "app_id": "APP_ID",
        "app_key": "APP_KEY",
        "Content-type": "application/json"
    }
)
print(r.json())

JavaScript / TypeScript

const response = await fetch("https://api.mathpix.com/v3/latex", {
  method: "POST",
  headers: {
    app_id: "APP_ID",
    app_key: "APP_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    src: "https://cdn.mathpix.com/examples/equation.jpg",
    formats: ["latex_simplified", "text"],
  }),
});
const result = await response.json();
console.log(result);

Go

body := bytes.NewBufferString(`{
    "src": "https://cdn.mathpix.com/examples/equation.jpg",
    "formats": ["latex_simplified", "text"]
}`)
req, _ := http.NewRequest("POST", "https://api.mathpix.com/v3/latex", body)
req.Header.Set("app_id", "APP_ID")
req.Header.Set("app_key", "APP_KEY")
req.Header.Set("Content-Type", "application/json")
resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()
result, _ := io.ReadAll(resp.Body)
fmt.Println(string(result))

Java

HttpClient client = HttpClient.newHttpClient();
String body = """
    {
      "src": "https://cdn.mathpix.com/examples/equation.jpg",
      "formats": ["latex_simplified", "text"]
    }
    """;
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.mathpix.com/v3/latex"))
    .header("app_id", "APP_ID")
    .header("app_key", "APP_KEY")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(body))
    .build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

Request parameters

You can send an image URL in a JSON body (src field) or upload a file via multipart form-data (with options_json).

src string (optional)

Image URL

tags string[] (optional)

Tags are lists of strings that can be used to identify results

async bool[] (optional)

This flag is to be used when sending non-interactive requests

formats string[]

String postprocessing formats (see Formatting)

ocr string[] (optional), default value is ["math"]

Process only math ["math"] or both math and text ["math", "text"].

format_options FormatOptions (optional)

Options for specific formats

skip_recrop bool (optional)

Force algorithm to consider whole image

confidence_threshold number in [0,1] (optional)

Set threshold for triggering confidence errors

beam_size number in [1,10] (optional)

Number of results to consider during recognition

n_best integer in [1,beam_size] (optional)

Number of highest-confidence results to return. Requires beam_size to be set

region Region (optional)

Specify the image area with pixel coordinates

callback Callback (optional)

Webhook for asynchronous result delivery

metadata object (optional)

Key-value object. Supports improve_mathpix for extra privacy controls.

include_detected_alphabets bool (optional)

Return detected alphabets

auto_rotate_confidence_threshold number in [0,1] (optional), default value is 0.99

Specifies threshold for auto rotating image to correct orientation. Can be disabled with a value of 1 (see Auto rotation section for details).

enable_blue_hsv_filter bool (optional), default value is false

Enables a special mode of image processing where it OCRs only blue hue text.

Formatting

Format	Description
text	text mode output, with math inside delimiters, eg. test \(x^2\), inline math by default
text_display	same as text, except uses block mode math instead of inline mode when in doubt
latex_normal	direct LaTeX representation of the input
latex_styled	modified output to improve the visual appearance such as adding '\left' and '\right' around parenthesized expressions that contain tall expressions like subscript or superscript
latex_simplified	modified output for symbolic processing such as shortening operator names, replacing long division with a fraction, and converting a column of operands into a single formula
latex_list	output split into a list of simplified strings to help process multiple equations
mathml	the MathML for the recognized math
asciimath	the AsciiMath for the recognized math
wolfram	a string compatible with the Wolfram Alpha engine

Format Options

The optional format_options request parameter allows customizing LaTeX result formats. The options value may specify:

transforms string[]

array of transformation names

math_delims [string, string]

[begin, end] delimiters for math mode.

Example

\( and \)

displaymath_delims [string, string]

[begin, end] delimiters for displaymath mode.

Example

\[ and \]

Available transforms:

Transform	Description
rm_spaces	omit spaces around LaTeX groups and other places where spaces are superfluous
rm_newlines	uses spaces instead of newlines between text lines in paragraphs
rm_fonts	omit mathbb, mathbf, mathcal, and mathrm commands
rm_style_syms	replace styled commands with unstyled versions, e.g., bigoplus becomes oplus
rm_text	omit text to the left or right of math
long_frac	convert longdiv to frac

note

rm_fonts and rm_style_syms are implicit in latex_normal, latex_simplified, and latex_list. The long_frac transformation is implicit in latex_simplified and latex_list.

Response body

request_id string

Request ID, for debugging purposes

version string

Model version used for processing

text string (optional)

Recognized text format

text_display string (optional)

Recognized text_display format

latex_normal string (optional)

Recognized latex_normal format

latex_simplified string (optional)

Recognized latex_simplified format

latex_styled string (optional)

Recognized latex_styled format

latex_list string[] (optional)

Recognized latex_list format

mathml string (optional)

Recognized MathML format

asciimath string (optional)

Recognized AsciiMath format

wolfram string (optional)

Recognized Wolfram format

position Region (optional)

Position object, pixel coordinates

detection_list string[] (optional)

Detects image properties (see Image Properties)

detection_map object (optional)

Object containing numeric values for each detection type. Keys include contains_chart, contains_diagram, contains_graph, contains_table, is_blank, is_inverted, is_not_math, is_printed.

image_height integer (optional)

Height of the processed image in pixels

image_width integer (optional)

Width of the processed image in pixels

error string (optional)

US locale error message

error_info ErrorInfo (optional)

Error info object

latex_confidence number in [0,1] (optional)

Estimated probability 100% correct

latex_confidence_rate number in [0,1] (optional)

Estimated confidence of output quality

candidates object[] (optional)

n_best results

detected_alphabets DetectedAlphabet[] (optional)

Detected alphabet flags

auto_rotate_confidence number in [0,1] (optional)

Estimated probability that image needs to be rotated, see Auto rotation

auto_rotate_degrees number in {0, 90, -90, 180} (optional)

Estimated angle of rotation in degrees to put image in correct orientation, see Auto rotation

Type definitions

Image Properties

Detection	Definition
contains_diagram	Contains a diagram.
is_printed	The image is taken of printed math, not handwritten math.
is_not_math	No valid equation was detected.