openapi: 3.2.0
info:
  title: LiteLLM Ocr API
  description: 'Proxy Server to call 100+ LLMs in the OpenAI format. **Customize Swagger Docs**


    👉 ```LiteLLM Admin Panel on /ui```. Create, Edit Keys with SSO. Having issues? Try ```Fallback Login```


    💸 ```LiteLLM Model Cost Map```.


    🔎 ```LiteLLM Model Hub```. See available models on the proxy. **Docs**'
  version: 1.102.1
tags:
- name: OCR
paths:
  /ocr:
    post:
      tags:
      - OCR
      summary: Ocr
      description: 'OCR endpoint for extracting text from documents and images.


        Supports two input modes:


        **1. JSON body** (Mistral OCR API compatible):

        ```bash

        curl -X POST "http://localhost:4000/v1/ocr" -H "Authorization: Bearer sk-1234" -H "Content-Type: application/json" -d ''{

        "model": "mistral-ocr",

        "document": {

        "type": "document_url",

        "document_url": "https://arxiv.org/pdf/2201.04234"

        }

        }''

        ```


        **2. Multipart form file upload**:

        ```bash

        curl -X POST "http://localhost:4000/v1/ocr" -H "Authorization: Bearer sk-1234" -F "model=mistral-ocr" -F "file=@document.pdf"

        ```


        Response format is normalized to the LiteLLM OCR schema by default. Providers

        that support it (Azure Document Intelligence) can return their own payload

        instead, with cost tracking unchanged, via `x-req-format: native` (or

        `"req_format": "native"` in the body).'
      operationId: ocr_ocr_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /v1/ocr:
    post:
      tags:
      - OCR
      summary: Ocr
      description: 'OCR endpoint for extracting text from documents and images.


        Supports two input modes:


        **1. JSON body** (Mistral OCR API compatible):

        ```bash

        curl -X POST "http://localhost:4000/v1/ocr" -H "Authorization: Bearer sk-1234" -H "Content-Type: application/json" -d ''{

        "model": "mistral-ocr",

        "document": {

        "type": "document_url",

        "document_url": "https://arxiv.org/pdf/2201.04234"

        }

        }''

        ```


        **2. Multipart form file upload**:

        ```bash

        curl -X POST "http://localhost:4000/v1/ocr" -H "Authorization: Bearer sk-1234" -F "model=mistral-ocr" -F "file=@document.pdf"

        ```


        Response format is normalized to the LiteLLM OCR schema by default. Providers

        that support it (Azure Document Intelligence) can return their own payload

        instead, with cost tracking unchanged, via `x-req-format: native` (or

        `"req_format": "native"` in the body).'
      operationId: ocr_v1_ocr_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
components:
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      description: Bearer token
      in: header
      name: x-litellm-api-key