RefineLoop Jobs

Create and manage RefineLoop XLIFF translation refinement jobs

List RefineLoop job history

GET

https://gw.ldxhub.io

/refineloop/jobs

Returns a list of jobs for the authenticated user, ordered by creation date descending. Use GET /refineloop/jobs/{job_id} to retrieve full details for a specific job.

List RefineLoop job history › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

List RefineLoop job history › Responses

A list of jobs

RefineLoopJobSummary[]

GET/refineloop/jobs

curl https://gw.ldxhub.io/refineloop/jobs \
  --header 'Authorization: Bearer <token>'

Example Responses

{
  "data": [
    {
      "job_id": "akobiov2sxoqs8nzylqm52202q7skw81",
      "file_id": "ako5rgx309ehwlbqprs8s2xxnsp0y85q",
      "model": "google/gemini-3.5-flash",
      "status": "completed",
      "progress": 100,
      "created_at": "2026-04-13T11:21:23Z",
      "updated_at": "2026-04-13T11:21:51Z",
      "completed_at": "2026-04-13T11:21:51Z",
      "expires_at": "2026-04-14T11:21:51Z",
      "usage": {
        "total_input_characters": 18412,
        "processed_input_characters": 18382,
        "skipped_characters": 30,
        "output_characters": 19647,
        "vector_bytes": 0
      }
    }
  ]
}

json

application/json

Create a RefineLoop job

POST

https://gw.ldxhub.io

/refineloop/jobs

Enqueues an asynchronous XLIFF translation refinement job. Upload your XLIFF file via POST /files first, then submit the file_id here. Returns 202 Accepted immediately with a job_id. Poll GET /refineloop/jobs/{job_id} to check completion. When completed, download the refined XLIFF via GET /files/{output_file_id}/content.

Create a RefineLoop job › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Create a RefineLoop job › Request Body

RefineLoopCreateJobRequest

model

string · required

Model ID obtained from GET /refineloop/models

file_id

string · required

File ID of the XLIFF file to process, obtained from POST /files

exclude_numeric_segments

boolean

If true, segments containing only numbers are skipped

Default: false

remove_hyphenation

boolean

If true, hyphenation in source text is removed before processing

Default: true

max_revisions

integer · min: 1 · max: 10

Maximum number of revision iterations per segment (1-10)

Default: 6

domain

string

Subject domain to guide translation review (e.g. "IR", "medical", "legal")

note_language

string

Language code for revision notes written by the AI (e.g. "ja", "en", "ko"). Defaults to the source language of the XLIFF file if not specified.

output_mode

string · enum

Controls what is included in the output XLIFF

Enum values:

full

translations

none

Default: full

custom_instructions

string

Additional instructions appended to the AI's base prompt

Create a RefineLoop job › Responses

Job accepted

Response returned immediately after job submission

JobCreateResponse

job_id

string

Unique job identifier. Use this to poll for results.

model

string

status

string · enum

Enum values:

queued

progress

number · float

created_at

string · date-time

updated_at

string · date-time

expires_at

string · date-time

POST/refineloop/jobs

curl https://gw.ldxhub.io/refineloop/jobs \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <token>' \
  --data '{
  "model": "google/gemini-3.5-flash",
  "file_id": "ako5rgx309ehwlbqprs8s2xxnsp0y85q",
  "max_revisions": 3,
  "domain": "IR",
  "note_language": "ja",
  "output_mode": "full",
  "custom_instructions": "専門用語は原文のまま残してください"
}'

Example Request Body

{
  "model": "google/gemini-3.5-flash",
  "file_id": "ako5rgx309ehwlbqprs8s2xxnsp0y85q",
  "max_revisions": 3,
  "domain": "IR",
  "note_language": "ja",
  "output_mode": "full",
  "custom_instructions": "専門用語は原文のまま残してください"
}

json

application/json

Example Responses

{
  "job_id": "akobiov2sxoqs8nzylqm52202q7skw81",
  "model": "google/gemini-3.5-flash",
  "status": "queued",
  "progress": 0,
  "created_at": "2026-04-13T11:21:23Z",
  "updated_at": "2026-04-13T11:21:23Z",
  "expires_at": "2026-04-14T11:21:23Z"
}

json

application/json

Get RefineLoop job status and results

GET

https://gw.ldxhub.io

/refineloop/jobs/{job_id}

Returns the current status of a RefineLoop job. Poll this endpoint until status is completed or failed. Recommended polling interval: 1-5 seconds. When status is completed, use output_file_id to download the refined XLIFF via GET /files/{output_file_id}/content. Results are retained for a limited period after completion (expires_at).

Get RefineLoop job status and results › path Parameters

job_id

string · required

The unique identifier of the job

Get RefineLoop job status and results › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Get RefineLoop job status and results › Responses

Job details

Full job details. Returned by GET /refineloop/jobs/{job_id}.

RefineLoopJobDetail

job_id

string

file_id

string

Input file ID

model

string

status

string · enum

Enum values:

queued

processing

completed

failed

progress

number · float

output_file_id

string

File ID of the refined XLIFF output. Present only when status is completed. Download via GET /files/{output_file_id}/content.

JobError

Job-level error. Present only when job status is failed.

created_at

string · date-time

updated_at

string · date-time

completed_at

string · date-time

expires_at

string · date-time

Usage

RefineLoop Models RenderOCR Engines

List RefineLoop job history

GET

https://gw.ldxhub.io

/refineloop/jobs

Returns a list of jobs for the authenticated user, ordered by creation date descending. Use GET /refineloop/jobs/{job_id} to retrieve full details for a specific job.

List RefineLoop job history › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

List RefineLoop job history › Responses

A list of jobs

RefineLoopJobSummary[]

Create a RefineLoop job

POST

https://gw.ldxhub.io

/refineloop/jobs

Create a RefineLoop job › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Create a RefineLoop job › Request Body

RefineLoopCreateJobRequest

model

string · required

Model ID obtained from GET /refineloop/models

file_id

string · required

File ID of the XLIFF file to process, obtained from POST /files

exclude_numeric_segments

boolean

If true, segments containing only numbers are skipped

Default: false

remove_hyphenation

boolean

If true, hyphenation in source text is removed before processing

Default: true

max_revisions

integer · min: 1 · max: 10

Maximum number of revision iterations per segment (1-10)

Default: 6

domain

string

Subject domain to guide translation review (e.g. "IR", "medical", "legal")

note_language

string

Language code for revision notes written by the AI (e.g. "ja", "en", "ko"). Defaults to the source language of the XLIFF file if not specified.

output_mode

string · enum

Controls what is included in the output XLIFF

Enum values:

full

translations

none

Default: full

custom_instructions

string

Additional instructions appended to the AI's base prompt

Create a RefineLoop job › Responses

Job accepted

Response returned immediately after job submission

JobCreateResponse

job_id

string

Unique job identifier. Use this to poll for results.

model

string

status

string · enum

Enum values:

queued

progress

number · float

created_at

string · date-time

updated_at

string · date-time

expires_at

string · date-time

Get RefineLoop job status and results

GET

https://gw.ldxhub.io

/refineloop/jobs/{job_id}

Get RefineLoop job status and results › path Parameters

job_id

string · required

The unique identifier of the job

Get RefineLoop job status and results › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Get RefineLoop job status and results › Responses

Job details

Full job details. Returned by GET /refineloop/jobs/{job_id}.

RefineLoopJobDetail

job_id

string

file_id

string

Input file ID

model

string

status

string · enum

Enum values:

queued

processing

completed

failed

progress

number · float

output_file_id

string

File ID of the refined XLIFF output. Present only when status is completed. Download via GET /files/{output_file_id}/content.

JobError

Job-level error. Present only when job status is failed.

created_at

string · date-time

updated_at

string · date-time

completed_at

string · date-time

expires_at

string · date-time

Usage