Skip to main content
POST
/
v1
/
ocr
Error
A valid request URL is required to generate request examples
{
  "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>",
    "provider": "openai",
    "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
    }
  }
}

Authorizations

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
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

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.

document_annotation_format
object

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

document_annotation_prompt
string

Custom prompt for document annotation

Response

Successful response

model
string
required

Model used to perform OCR

pages
object[]
required

Processed pages with extracted content

usage_info
object
document_annotation
string

Document-level annotation if requested

extra_fields
object

Additional fields included in responses