Skip to content
ParseHawkParseHawk Developer Docs

Get a parse job

GET
/v1/parse-jobs/{job_id}
Code sample: curl
API="${PARSEHAWK_API_URL:-http://127.0.0.1:8000}"
curl --fail --silent --show-error "$API/v1/parse-jobs/parse_job_..." | jq .

Retrieve the current state, Markdown result, or failure details for one parse job.

Parameters

Section titled “Parameters”

Path Parameters

Section titled “Path Parameters”
job_id
required
Job Id

Immutable parse job identifier.

string

Immutable parse job identifier.

Responses

Section titled “Responses”

200

Section titled “200”

Successful Response

Media typeapplication/json
ParseJobResponse

Current state and eventual Markdown result of one parse job.

object
id
required
Id

Immutable parse job identifier.

string
parser_id
required
Parser Id

Immutable parser identifier used by the job.

string
file_id
required
File Id

Input file identifier.

string
parser_snapshot
required
ParserSnapshotResponse

Immutable parser configuration captured when the job was created.

object
parser_id
required
Parser Id

Immutable parser identifier.

string
name
required
Name

Stable parser name at enqueue time.

string
display_name
required
Display Name

Parser label at enqueue time.

string
output_format
required
ParserOutputFormat

Output format at enqueue time.

string
Allowed values: markdown
instructions
required
Instructions

Parsing instructions at enqueue time.

string
reasoning_effort
required
Any of:
ReasoningEffort

Explicit reasoning effort for an extractor’s or parser’s model.

The values mirror OpenAI’s reasoning_effort parameter. Extractors store None by default, which means “send no reasoning parameter and use the model’s own default” — the only setting that is safe for every model. Which explicit values a model accepts is the provider’s call; incompatible pairs surface the provider’s error at extraction time.

string
Allowed values: none minimal low medium high xhigh
provider_name
required
Any of:
ProviderName

The fixed set of model providers ParseHawk ships.

Providers are preconfigured and configurable, not user-creatable, so the name doubles as the stable identifier extractors reference and as the discriminator the engine factory switches on.

string
Allowed values: openai microsoft_foundry openai_compatible_api
model
required
Any of:
string
provider_name_used
required
Any of:
ProviderName

The fixed set of model providers ParseHawk ships.

Providers are preconfigured and configurable, not user-creatable, so the name doubles as the stable identifier extractors reference and as the discriminator the engine factory switches on.

string
Allowed values: openai microsoft_foundry openai_compatible_api
model_used
required
Any of:
string
reasoning_effort_used
required
Any of:
ReasoningEffort

Explicit reasoning effort for an extractor’s or parser’s model.

The values mirror OpenAI’s reasoning_effort parameter. Extractors store None by default, which means “send no reasoning parameter and use the model’s own default” — the only setting that is safe for every model. Which explicit values a model accepts is the provider’s call; incompatible pairs surface the provider’s error at extraction time.

string
Allowed values: none minimal low medium high xhigh
model_adapter_used
required
Any of:
string
status
required
JobStatus

Current job lifecycle state.

string
Allowed values: queued running completed failed canceling deleting canceled
result
required
Any of:
ParseResultResponse

Canonical Markdown result for a completed parse job.

object
format
required
ParserOutputFormat

Result content format.

string
Allowed values: markdown
content
required
Content

All page content joined by an HTML page-break comment.

string
page_count
required
Page Count

Number of parsed source pages.

integer
>= 1
pages
required
Pages

Canonical one-based per-page Markdown output.

Array<object>
ParsePageResultResponse

Markdown output for one source page.

object
page_number
required
Page Number

One-based source page number.

integer
>= 1
content
required
Content

Markdown transcription for this page.

string
error
required
Any of:
ParseErrorResponse

Terminal parsing error stored with a failed job.

object
message
required
Message

Human-readable failure message.

string
code
required
Code

Stable machine-readable failure code.

string
created_at
required
Created At

UTC creation time.

string format: date-time
started_at
required
Any of:
string format: date-time
completed_at
required
Any of:
string format: date-time
Example
{
  "parser_snapshot": {
    "output_format": "markdown",
    "reasoning_effort": "none",
    "provider_name": "openai"
  },
  "provider_name_used": "openai",
  "reasoning_effort_used": "none",
  "status": "queued",
  "result": {
    "format": "markdown"
  }
}

404

Section titled “404”

The requested ParseHawk resource does not exist.

Media typeapplication/json
ApiErrorResponse

Error returned by request validation or a ParseHawk domain service.

object
code
Any of:
string
detail
required
Any of:
string
Examplegenerated
{
  "code": "example",
  "detail": [
    {}
  ]
}

422

Section titled “422”

Validation Error

Media typeapplication/json
HTTPValidationError
object
detail
Detail
Array<object>
ValidationError
object
loc
required
Location
Array
msg
required
Message
string
type
required
Error Type
string
input
Input
ctx
Context
object
Examplegenerated
{
  "detail": [
    {
      "loc": [
        "example"
      ],
      "msg": "example",
      "type": "example",
      "input": "example",
      "ctx": {}
    }
  ]
}

500

Section titled “500”

Unexpected server error.

Media typeapplication/json
ApiErrorResponse

Error returned by request validation or a ParseHawk domain service.

object
code
Any of:
string
detail
required
Any of:
string
Examplegenerated
{
  "code": "example",
  "detail": [
    {}
  ]
}

503

Section titled “503”

Persistence is temporarily busy and the request can be retried.

Media typeapplication/json
ApiErrorResponse

Error returned by request validation or a ParseHawk domain service.

object
code
Any of:
string
detail
required
Any of:
string
Examplegenerated
{
  "code": "example",
  "detail": [
    {}
  ]
}