OCR

POST 
/v1/tools/ocr

Recognize the text in a PDF, Word or PowerPoint document or in an image, and return the result page by page. The file is not stored in the Files API. See the OCR guide for the limits, errors and billing.

Request

multipart/form-data

Body

required

file binaryrequired

The file to recognize, sent with a file name. See the OCR guide for the supported formats and limits.

purpose stringrequired

Possible values: text_recognition, rich_layout_recognition

text_recognition extracts text directly from Word and PowerPoint files without images and recognizes other files page by page. rich_layout_recognition recognizes every file page by page. See the OCR guide for the output.

Responses

200

OK, returns the recognition result of every page.

application/json

Schema

Schema

id stringrequired

The recognition ID, of the form ocr-....

object stringrequired

Possible values: ocr.result

The object type, which is always ocr.result.

created integerrequired

The Unix timestamp (in seconds) of when the recognition was created.

purpose stringrequired

Possible values: text_recognition, rich_layout_recognition

The purpose of the request.

page_count integerrequired

The number of pages, equal to the length of pages.

pages

object[]

required

The recognition result of every page, in page order.

Array [

index integerrequired

The page number, starting from 0.

text stringrequired

The raw model output for the page, without any cleanup.

finish_reason stringrequired

Possible values: stop, length

stop when the page was recognized completely; length when the output reached the limit and the page text is incomplete.

]

usage

object

required

The token usage of all pages. For reference only; not used for billing.

input_tokens integerrequired

The OCR input tokens of all pages. For reference only; not used for billing.

output_tokens integerrequired

The OCR output tokens of all pages. For reference only; not used for billing.

total_tokens integerrequired

The sum of input_tokens and output_tokens.

Example

{
  "id": "ocr-9b2f4c1e-5d7a-4e3b-8f21-6c0a9d4e7b12",
  "object": "ocr.result",
  "created": 1762790000,
  "purpose": "text_recognition",
  "page_count": 1,
  "pages": [
    {
      "index": 0,
      "text": "DeepSeek API\n\nThe DeepSeek API uses an API format compatible with OpenAI and Anthropic.",
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "input_tokens": 1536,
    "output_tokens": 412,
    "total_tokens": 1948
  }
}

Loading...