Perform OCR

Extracts text and content from documents or images using optical character recognition. Supports PDF URLs, base64-encoded documents, and image URLs.

POST /v1/ocr

Error

A valid request URL is required to generate request examples

200

{
  "model": "<string>",
  "pages": [
    {
      "index": 1,
      "markdown": "<string>",
      "images": [
        {
          "id": "<string>",
          "top_left_x": 123,
          "top_left_y": 123,
          "bottom_right_x": 123,
          "bottom_right_y": 123,
          "image_base64": "<string>"
        }
      ],
      "dimensions": {
        "dpi": 123,
        "height": 123,
        "width": 123
      },
      "tables": [
        {}
      ],
      "header": "<string>",
      "footer": "<string>",
      "confidence_scores": {
        "average_page_confidence_score": 123,
        "minimum_page_confidence_score": 123,
        "word_confidence_scores": [
          123
        ]
      }
    }
  ],
  "usage_info": {
    "pages_processed": 123,
    "doc_size_bytes": 123
  },
  "document_annotation": "<string>",
  "extra_fields": {
    "request_type": "<string>",
    "model_requested": "<string>",
    "model_deployment": "<string>",
    "latency": 123,
    "chunk_index": 123,
    "raw_request": {},
    "raw_response": {},
    "cache_debug": {
      "cache_hit": true,
      "cache_id": "<string>",
      "hit_type": "<string>",
      "requested_provider": "<string>",
      "requested_model": "<string>",
      "provider_used": "<string>",
      "model_used": "<string>",
      "input_tokens": 123,
      "threshold": 123,
      "similarity": 123
    }
  }
}

{
  "event_id": "<string>",
  "type": "<string>",
  "is_bifrost_error": true,
  "status_code": 123,
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "event_id": "<string>"
  },
  "extra_fields": {
    "model_requested": "<string>",
    "request_type": "<string>"
  }
}

{
  "event_id": "<string>",
  "type": "<string>",
  "is_bifrost_error": true,
  "status_code": 123,
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "event_id": "<string>"
  },
  "extra_fields": {
    "model_requested": "<string>",
    "request_type": "<string>"
  }
}

Authorizations

BearerAuthBasicAuthVirtualKeyAuthApiKeyAuth

Authorization · string · header · required

Bearer token authentication. Use your provider API key or Bifrost authentication token. Virtual keys (prefixed with sk-bf-) can also be passed here.

Body

application/json

model · string · required

Model in provider/model format

Example:

"mistral/mistral-ocr-latest"

document · object · required

Option 1

Option 2

Show child attributes

id · string

Optional unique identifier for the request

fallbacks · string[]

Fallback models in provider/model format

include_image_base64 · boolean

Whether to include base64-encoded images in the response

pages · integer[]

Specific page indices to process (0-based)

Required range: x >= 0

image_limit · integer

Maximum number of images to extract per page

Required range: x >= 1

image_min_size · integer

Minimum image size in pixels to extract

Required range: x >= 1

table_format · string

Format for extracted tables (e.g., "markdown", "html")

extract_header · boolean

Whether to extract page headers

extract_footer · boolean

Whether to extract page footers

confidence_scores_granularity · enum<string>

Granularity of confidence scores to include in the response

Available options: page, block, word, document

bbox_annotation_format · object

Format for bounding box annotations. Supports text, json_object, and json_schema modes.

Option 1

Option 2

Show child attributes

document_annotation_format · object

Format for document-level annotations. Supports text, json_object, and json_schema modes.

Option 1

Option 2

Show child attributes

document_annotation_prompt · string

Custom prompt for document annotation

Response

200

application/json

Successful response

model · string · required

Model used to perform OCR

pages · object[] · required

Processed pages with extracted content

Show child attributes

usage_info · object

Show child attributes

document_annotation · string

Document-level annotation if requested

extra_fields · object

Additional fields included in responses

Show child attributes