> ## Documentation Index
> Fetch the complete documentation index at: https://docs.context.dev/llms.txt
> Use this file to discover all available pages before exploring further.
> ## Agent Instructions
> Setting up Context.dev for a user? Follow https://docs.context.dev/agent-quickstart.md. MCP clients sign in with OAuth and need no API key; application code reads CONTEXT_DEV_API_KEY.
# Parse a file
> Convert uploaded file bytes into Markdown and optional HTML.
From 1 credit
See the [guide](/parse/overview) for examples and usage.
## OpenAPI
````yaml POST /parse
openapi: 3.1.0
info:
title: Context.dev API
description: >-
Scrape, crawl, search, and monitor websites, and retrieve brand, people, and
news data.
version: 1.0.0
servers:
- url: https://api.context.dev/v1
security: []
tags:
- name: Webhooks
description: Inspect and retry batch and monitor webhook deliveries.
- name: Logs
description: Read your organization's API request logs.
- name: Agent Feedback
description: Report API issues and documentation mismatches.
- name: Batches
description: Scrape many pages or crawl a site asynchronously.
- name: Monitors
description: Watch websites for exact or meaningful changes.
- name: News
description: Search live and historical news about a company.
- name: Answers
description: Answer a research task from the live web in the JSON shape you ask for.
paths:
/parse:
post:
tags:
- Parsing
summary: Parse a file
description: Convert uploaded file bytes into Markdown and optional HTML.
parameters:
- schema:
type: string
enum:
- txt
- text
- md
- markdown
- html
- htm
- xhtml
- xml
- rss
- atom
- csv
- tsv
- yaml
- yml
- py
- java
- js
- jsx
- mjs
- cjs
- json
- jsonl
- ndjson
- php
- sh
- bash
- zsh
- fish
- rb
- ts
- tsx
- rtf
- srt
- css
- scss
- less
- styl
- sass
- svg
- pdf
- docx
- doc
- xlsx
- xlsm
- xlsb
- xltx
- xltm
- xls
- pptx
- pptm
- ppsx
- ppsm
- potx
- potm
- ppt
- pps
- pot
- jpg
- jpeg
- jpe
- png
- gif
- bmp
- tiff
- tif
- webp
- ppm
- pbm
- pgm
- pnm
description: >-
Optional file extension hint, such as pdf, docx, xlsx, pptx, html,
json, csv, md, py, rtf, jpg, png, or txt.
required: false
description: >-
Optional file extension hint, such as pdf, docx, xlsx, pptx, html,
json, csv, md, py, rtf, jpg, png, or txt.
name: extension
in: query
- schema:
type: boolean
default: true
description: Preserve hyperlinks in Markdown output
required: false
description: Preserve hyperlinks in Markdown output
name: includeLinks
in: query
- schema:
type: boolean
default: false
description: Include image references in Markdown output
required: false
description: Include image references in Markdown output
name: includeImages
in: query
- schema:
type: boolean
default: true
description: Shorten base64-encoded image data in the Markdown output
required: false
description: Shorten base64-encoded image data in the Markdown output
name: shortenBase64Images
in: query
- schema:
type: boolean
default: false
description: Extract only the main content from HTML-like inputs
required: false
description: Extract only the main content from HTML-like inputs
name: useMainContentOnly
in: query
- schema:
type: boolean
default: false
description: >-
Read text from images and scanned PDF pages. PDF page ranges still
apply.
required: false
description: >-
Read text from images and scanned PDF pages. PDF page ranges still
apply.
name: ocr
in: query
- schema:
type: object
properties:
start:
type: integer
minimum: 1
description: >-
First 1-based PDF page to parse. When omitted, parsing starts
at the first page.
end:
type: integer
minimum: 1
description: >-
Last 1-based PDF page to parse. When omitted, parsing ends at
the last page. Must be greater than or equal to start when
both are provided.
additionalProperties: false
description: >-
PDF page-range options as a JSON object, e.g. {"start": 2, "end":
5}.
required: false
description: >-
PDF page-range options as a JSON object, e.g. {"start": 2, "end":
5}.
name: pdf
in: query
- schema:
type: string
minLength: 1
maxLength: 100
description: Optional client identifier used for usage attribution.
required: false
description: Optional client identifier used for usage attribution.
name: client
in: query
- schema:
type: string
enum:
- enabled
- disabled
default: disabled
description: >-
`enabled` turns on zero data retention. Returns 403
`ZDR_NOT_ENABLED` unless your organization has ZDR.
required: false
description: >-
`enabled` turns on zero data retention. Returns 403
`ZDR_NOT_ENABLED` unless your organization has ZDR.
name: zdr
in: query
- $ref: '#/components/parameters/RequestTags'
requestBody:
required: true
description: Raw file bytes, up to 50 MiB.
content:
application/octet-stream:
schema:
type: string
format: binary
application/pdf:
schema:
type: string
format: binary
'*/*':
schema:
type: string
format: binary
responses:
'200':
description: Successful response
headers:
X-Request-Id:
$ref: '#/components/headers/RequestId'
X-RateLimit-Limit:
$ref: '#/components/headers/RateLimitLimit'
X-RateLimit-Remaining:
$ref: '#/components/headers/RateLimitRemaining'
X-RateLimit-Reset:
$ref: '#/components/headers/RateLimitReset'
X-RateLimit-Mode:
$ref: '#/components/headers/RateLimitMode'
X-Context-ZDR:
description: >-
Present with the value true when zero data retention was
requested and honored.
schema:
type: string
enum:
- 'true'
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
enum:
- true
description: Indicates success
markdown:
type: string
description: Input bytes converted to GitHub Flavored Markdown
type:
type: string
enum:
- html
- xml
- json
- jsonl
- text
- csv
- tsv
- markdown
- yaml
- python
- java
- javascript
- php
- shell
- ruby
- typescript
- rtf
- srt
- css
- scss
- less
- stylus
- sass
- svg
- pdf
- docx
- doc
- xlsx
- xls
- pptx
- ppt
- jpg
- png
- gif
- bmp
- tiff
- webp
- ppm
- pbm
- pgm
- pnm
description: Detected content type used for parsing
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
request_id:
$ref: '#/components/schemas/RequestId'
required:
- success
- markdown
- type
- request_id
'400':
description: Invalid input or no parseable content
headers:
X-Request-Id:
$ref: '#/components/headers/RequestId'
X-RateLimit-Limit:
$ref: '#/components/headers/RateLimitLimit'
X-RateLimit-Remaining:
$ref: '#/components/headers/RateLimitRemaining'
X-RateLimit-Reset:
$ref: '#/components/headers/RateLimitReset'
X-RateLimit-Mode:
$ref: '#/components/headers/RateLimitMode'
content:
application/json:
schema:
type: object
properties:
message:
type: string
error_code:
type: string
enum:
- INPUT_VALIDATION_ERROR
- WEBSITE_ACCESS_ERROR
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
request_id:
$ref: '#/components/schemas/RequestId'
required:
- request_id
'413':
description: Request body exceeds the 50 MiB upload limit
headers:
X-Request-Id:
$ref: '#/components/headers/RequestId'
X-RateLimit-Limit:
$ref: '#/components/headers/RateLimitLimit'
X-RateLimit-Remaining:
$ref: '#/components/headers/RateLimitRemaining'
X-RateLimit-Reset:
$ref: '#/components/headers/RateLimitReset'
X-RateLimit-Mode:
$ref: '#/components/headers/RateLimitMode'
content:
application/json:
schema:
type: object
properties:
message:
type: string
error_code:
type: string
enum:
- INPUT_VALIDATION_ERROR
'415':
description: Unsupported content type
headers:
X-Request-Id:
$ref: '#/components/headers/RequestId'
X-RateLimit-Limit:
$ref: '#/components/headers/RateLimitLimit'
X-RateLimit-Remaining:
$ref: '#/components/headers/RateLimitRemaining'
X-RateLimit-Reset:
$ref: '#/components/headers/RateLimitReset'
X-RateLimit-Mode:
$ref: '#/components/headers/RateLimitMode'
content:
application/json:
schema:
type: object
properties:
message:
type: string
error_code:
type: string
enum:
- UNSUPPORTED_CONTENT
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
request_id:
$ref: '#/components/schemas/RequestId'
required:
- request_id
'500':
description: Internal server error
headers:
X-Request-Id:
$ref: '#/components/headers/RequestId'
X-RateLimit-Limit:
$ref: '#/components/headers/RateLimitLimit'
X-RateLimit-Remaining:
$ref: '#/components/headers/RateLimitRemaining'
X-RateLimit-Reset:
$ref: '#/components/headers/RateLimitReset'
X-RateLimit-Mode:
$ref: '#/components/headers/RateLimitMode'
content:
application/json:
schema:
type: object
properties:
message:
type: string
error_code:
type: string
enum:
- INTERNAL_ERROR
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
request_id:
$ref: '#/components/schemas/RequestId'
required:
- request_id
'503':
description: >-
Document parsing is at capacity. Retry after the delay in
Retry-After.
headers:
X-Request-Id:
$ref: '#/components/headers/RequestId'
X-RateLimit-Limit:
$ref: '#/components/headers/RateLimitLimit'
X-RateLimit-Remaining:
$ref: '#/components/headers/RateLimitRemaining'
X-RateLimit-Reset:
$ref: '#/components/headers/RateLimitReset'
X-RateLimit-Mode:
$ref: '#/components/headers/RateLimitMode'
Retry-After:
description: Seconds to wait before retrying the upload
schema:
type: integer
minimum: 1
content:
application/json:
schema:
type: object
properties:
message:
type: string
error_code:
type: string
enum:
- INTERNAL_ERROR
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
request_id:
$ref: '#/components/schemas/RequestId'
required:
- request_id
security:
- bearerAuth: []
components:
parameters:
RequestTags:
name: tags
in: query
required: false
style: form
explode: false
schema:
$ref: '#/components/schemas/RequestTags'
description: >-
Comma-separated labels for filtering usage, e.g.
`production,team-alpha`.
example: production,team-alpha
headers:
RequestId:
description: Unique ID of this request; also `request_id` in JSON bodies.
schema:
type: string
format: uuid
RateLimitLimit:
description: >-
Maximum request units per minute, or maximum concurrent requests when
X-RateLimit-Mode is concurrency.
schema:
type: integer
minimum: 1
RateLimitRemaining:
description: >-
Request units remaining in the current minute, or concurrent requests
still available when X-RateLimit-Mode is concurrency.
schema:
type: integer
minimum: 0
RateLimitReset:
description: >-
Unix timestamp in seconds when the per-minute rate limit resets. Omitted
for concurrency limits.
schema:
type: integer
RateLimitMode:
description: >-
Set to concurrency when the organization is limited by concurrent
requests. Omitted for per-minute limits.
schema:
type: string
enum:
- concurrency
schemas:
KeyMetadata:
type: object
properties:
credits_consumed:
type: integer
description: Credits charged for this request.
credits_remaining:
type: integer
description: Credits remaining for your organization.
required:
- credits_consumed
- credits_remaining
description: Credits this request used and your remaining balance.
RequestId:
type: string
format: uuid
description: >-
Unique ID of this request, also in `X-Request-Id`. Include it when
contacting support.
example: 3f1c2a6e-8b4d-4c1e-9f0a-2d7b5e6c8a91
RequestTags:
type: array
items:
type: string
minLength: 1
maxLength: 50
maxItems: 20
description: Labels for filtering usage in the dashboard.
example:
- production
- team-alpha
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: >-
Send `Authorization: Bearer `. Keys have full access unless
restricted to scopes.
````