Re-run a finished pipeline job from a later step

curl --request POST \
  --url https://api.varg.ai/v2/jobs/{id}/rerun \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "step": "extend",
  "overrides": {
    "prompt": "the camera keeps pushing in"
  }
}
'

import requests

url = "https://api.varg.ai/v2/jobs/{id}/rerun"

payload = {
    "step": "extend",
    "overrides": { "prompt": "the camera keeps pushing in" }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({step: 'extend', overrides: {prompt: 'the camera keeps pushing in'}})
};

fetch('https://api.varg.ai/v2/jobs/{id}/rerun', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.varg.ai/v2/jobs/{id}/rerun",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'step' => 'extend',
    'overrides' => [
        'prompt' => 'the camera keeps pushing in'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.varg.ai/v2/jobs/{id}/rerun"

	payload := strings.NewReader("{\n  \"step\": \"extend\",\n  \"overrides\": {\n    \"prompt\": \"the camera keeps pushing in\"\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.varg.ai/v2/jobs/{id}/rerun")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"step\": \"extend\",\n  \"overrides\": {\n    \"prompt\": \"the camera keeps pushing in\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.varg.ai/v2/jobs/{id}/rerun")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"step\": \"extend\",\n  \"overrides\": {\n    \"prompt\": \"the camera keeps pushing in\"\n  }\n}"

response = http.request(request)
puts response.read_body

{
  "id": "job_a1b2c3d4e5f6",
  "status": "queued",
  "stage": "queued",
  "attempts": [
    {
      "n": 1,
      "provider": "byteplus",
      "model_key": "byteplus:dreamina-seedance-2-5-260628",
      "status": "running",
      "reason": "real person in the reference images",
      "reason_code": "content_privacy",
      "references_uploaded": 123,
      "resubmitted": true,
      "started_at": "2023-11-07T05:31:56Z",
      "ended_at": "2023-11-07T05:31:56Z"
    }
  ],
  "tool": "tool_2001a2b3c4d5",
  "input": {},
  "output": {
    "version": "v1",
    "outputs": [
      {
        "url": "<string>",
        "file_id": "<string>",
        "media_type": "video/mp4",
        "size_bytes": 123,
        "thumbnail_url": "<string>",
        "data": "<unknown>",
        "raw": "<unknown>"
      }
    ]
  },
  "error": "<string>",
  "progress_message": "stitching 3/8 (40%)",
  "progress": 123,
  "progress_metadata": {},
  "step_state": {
    "current_step": "extend",
    "steps": {}
  },
  "estimated_duration_ms": 123,
  "estimated_cost_cents": 123,
  "actual_cost_cents": 123,
  "pricing": {
    "estimated": 123,
    "actual": 123,
    "billing": "<string>",
    "cached": true,
    "billed_units": {
      "images": 1
    },
    "pricing_id": "<string>"
  },
  "provider": "fal",
  "provider_model": "fal:flux_schnell",
  "provider_status": "<string>",
  "provider_job_id": "<string>",
  "completed_by_provider_model_id": "<string>",
  "last_attempt_provider_model_id": "<string>",
  "workspace_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "started_at": "2023-11-07T05:31:56Z",
  "completed_at": "2023-11-07T05:31:56Z",
  "warnings": [
    "<string>"
  ],
  "urls": {
    "self": "<string>",
    "status": "<string>",
    "refresh": "<string>",
    "cancel": "<string>",
    "retry": "<string>",
    "confirm": "<string>",
    "rerun": "<string>"
  }
}

{
  "id": "job_a1b2c3d4e5f6",
  "status": "queued",
  "stage": "queued",
  "attempts": [],
  "tool": "tool_a1b2c3d4e5f6",
  "input": {
    "model": "flux_schnell",
    "prompt": "a cat astronaut"
  },
  "output": null,
  "error": null,
  "progress_message": null,
  "progress": null,
  "progress_metadata": null,
  "step_state": null,
  "estimated_duration_ms": 8000,
  "estimated_cost_cents": 4,
  "actual_cost_cents": null,
  "pricing": {
    "estimated": 4,
    "actual": null,
    "billing": "metered",
    "cached": null,
    "billed_units": null,
    "pricing_id": "ppr_abc123"
  },
  "provider": "fal",
  "provider_model": "fal:flux_schnell",
  "provider_status": null,
  "provider_job_id": null,
  "completed_by_provider_model_id": null,
  "last_attempt_provider_model_id": null,
  "workspace_id": null,
  "created_at": "2026-07-01T10:00:00Z",
  "started_at": null,
  "completed_at": null,
  "urls": {
    "self": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6",
    "status": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6/status",
    "refresh": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6/refresh",
    "cancel": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6/cancel",
    "retry": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6/retry"
  }
}

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid or missing API key or JWT"
  }
}

{
  "error": {
    "code": "insufficient_balance",
    "message": "Needs 40 credits; 25 available right now (60 on hold for 2 running jobs)",
    "details": {
      "needed_cents": 40,
      "available_cents": 25,
      "reserved_cents": 60,
      "total_cents": 85,
      "held_jobs": 2,
      "job_id": "job_a1b2c3d4e5f6"
    }
  }
}

{
  "error": {
    "code": "model_not_found",
    "message": "Unknown model: flux-shnell",
    "details": "<unknown>"
  }
}

{
  "error": {
    "code": "model_not_found",
    "message": "Unknown model: flux-shnell",
    "details": "<unknown>"
  }
}

{
  "error": {
    "code": "model_not_found",
    "message": "Unknown model: flux-shnell",
    "details": "<unknown>"
  }
}

{
  "error": {
    "code": "model_not_found",
    "message": "Unknown model: flux-shnell",
    "details": "<unknown>"
  }
}

Jobs

Re-run a finished pipeline job from a later step

Regenerates one step of a finished multi-step pipeline job (“redo part 2”) without paying for the earlier steps again. Creates a new job with the source job’s input (plus overrides); the steps before step are carried over from the source job at no cost, and only step and the steps after it run and bill. The source job is not changed.

The source job must be finished (completed, failed or cancelled) and be a multi-step pipeline job. step must be a later step of that pipeline, not the first one (re-running the first step is a new pipeline job). overrides cannot switch the pipeline model.

The response is the same as creating a pipeline job: 202 with the new job, or 200 when Idempotency-Key matches an existing job. Errors of the pipeline create path (insufficient balance, rate limits) apply too.

POST

jobs

{id}

rerun

Re-run a finished pipeline job from a later step

curl --request POST \
  --url https://api.varg.ai/v2/jobs/{id}/rerun \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "step": "extend",
  "overrides": {
    "prompt": "the camera keeps pushing in"
  }
}
'

import requests

url = "https://api.varg.ai/v2/jobs/{id}/rerun"

payload = {
    "step": "extend",
    "overrides": { "prompt": "the camera keeps pushing in" }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({step: 'extend', overrides: {prompt: 'the camera keeps pushing in'}})
};

fetch('https://api.varg.ai/v2/jobs/{id}/rerun', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.varg.ai/v2/jobs/{id}/rerun",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'step' => 'extend',
    'overrides' => [
        'prompt' => 'the camera keeps pushing in'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.varg.ai/v2/jobs/{id}/rerun"

	payload := strings.NewReader("{\n  \"step\": \"extend\",\n  \"overrides\": {\n    \"prompt\": \"the camera keeps pushing in\"\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.varg.ai/v2/jobs/{id}/rerun")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"step\": \"extend\",\n  \"overrides\": {\n    \"prompt\": \"the camera keeps pushing in\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.varg.ai/v2/jobs/{id}/rerun")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"step\": \"extend\",\n  \"overrides\": {\n    \"prompt\": \"the camera keeps pushing in\"\n  }\n}"

response = http.request(request)
puts response.read_body

{
  "id": "job_a1b2c3d4e5f6",
  "status": "queued",
  "stage": "queued",
  "attempts": [
    {
      "n": 1,
      "provider": "byteplus",
      "model_key": "byteplus:dreamina-seedance-2-5-260628",
      "status": "running",
      "reason": "real person in the reference images",
      "reason_code": "content_privacy",
      "references_uploaded": 123,
      "resubmitted": true,
      "started_at": "2023-11-07T05:31:56Z",
      "ended_at": "2023-11-07T05:31:56Z"
    }
  ],
  "tool": "tool_2001a2b3c4d5",
  "input": {},
  "output": {
    "version": "v1",
    "outputs": [
      {
        "url": "<string>",
        "file_id": "<string>",
        "media_type": "video/mp4",
        "size_bytes": 123,
        "thumbnail_url": "<string>",
        "data": "<unknown>",
        "raw": "<unknown>"
      }
    ]
  },
  "error": "<string>",
  "progress_message": "stitching 3/8 (40%)",
  "progress": 123,
  "progress_metadata": {},
  "step_state": {
    "current_step": "extend",
    "steps": {}
  },
  "estimated_duration_ms": 123,
  "estimated_cost_cents": 123,
  "actual_cost_cents": 123,
  "pricing": {
    "estimated": 123,
    "actual": 123,
    "billing": "<string>",
    "cached": true,
    "billed_units": {
      "images": 1
    },
    "pricing_id": "<string>"
  },
  "provider": "fal",
  "provider_model": "fal:flux_schnell",
  "provider_status": "<string>",
  "provider_job_id": "<string>",
  "completed_by_provider_model_id": "<string>",
  "last_attempt_provider_model_id": "<string>",
  "workspace_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "started_at": "2023-11-07T05:31:56Z",
  "completed_at": "2023-11-07T05:31:56Z",
  "warnings": [
    "<string>"
  ],
  "urls": {
    "self": "<string>",
    "status": "<string>",
    "refresh": "<string>",
    "cancel": "<string>",
    "retry": "<string>",
    "confirm": "<string>",
    "rerun": "<string>"
  }
}

{
  "id": "job_a1b2c3d4e5f6",
  "status": "queued",
  "stage": "queued",
  "attempts": [],
  "tool": "tool_a1b2c3d4e5f6",
  "input": {
    "model": "flux_schnell",
    "prompt": "a cat astronaut"
  },
  "output": null,
  "error": null,
  "progress_message": null,
  "progress": null,
  "progress_metadata": null,
  "step_state": null,
  "estimated_duration_ms": 8000,
  "estimated_cost_cents": 4,
  "actual_cost_cents": null,
  "pricing": {
    "estimated": 4,
    "actual": null,
    "billing": "metered",
    "cached": null,
    "billed_units": null,
    "pricing_id": "ppr_abc123"
  },
  "provider": "fal",
  "provider_model": "fal:flux_schnell",
  "provider_status": null,
  "provider_job_id": null,
  "completed_by_provider_model_id": null,
  "last_attempt_provider_model_id": null,
  "workspace_id": null,
  "created_at": "2026-07-01T10:00:00Z",
  "started_at": null,
  "completed_at": null,
  "urls": {
    "self": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6",
    "status": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6/status",
    "refresh": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6/refresh",
    "cancel": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6/cancel",
    "retry": "https://api.varg.ai/v2/jobs/job_a1b2c3d4e5f6/retry"
  }
}

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid or missing API key or JWT"
  }
}

{
  "error": {
    "code": "insufficient_balance",
    "message": "Needs 40 credits; 25 available right now (60 on hold for 2 running jobs)",
    "details": {
      "needed_cents": 40,
      "available_cents": 25,
      "reserved_cents": 60,
      "total_cents": 85,
      "held_jobs": 2,
      "job_id": "job_a1b2c3d4e5f6"
    }
  }
}

{
  "error": {
    "code": "model_not_found",
    "message": "Unknown model: flux-shnell",
    "details": "<unknown>"
  }
}

{
  "error": {
    "code": "model_not_found",
    "message": "Unknown model: flux-shnell",
    "details": "<unknown>"
  }
}

{
  "error": {
    "code": "model_not_found",
    "message": "Unknown model: flux-shnell",
    "details": "<unknown>"
  }
}

{
  "error": {
    "code": "model_not_found",
    "message": "Unknown model: flux-shnell",
    "details": "<unknown>"
  }
}

Authorizations

Authorization

string

header

required

varg API key (varg_...). Get one at app.varg.ai or run bunx vargai login. App sessions may alternatively send a Supabase JWT.

Headers

Idempotency-Key

string

Any unique string. Retrying a request with the same key returns the existing job (HTTP 200) instead of creating and charging a new one (HTTP 202).

X-Workspace-Id

string

Folder id (uuid) or slug. The job's output is filed into this folder when the job completes. An unknown folder returns 404 workspace_not_found and no job is created. If you cannot set headers, send a top-level workspace_id field in the JSON body instead. Not part of the generation input, so it does not affect caching.

Path Parameters

string

required

Pattern: ^job_

Body

application/json

step

string

required

Key of the pipeline step to run again. Must come after the first step.

Minimum string length: 1

Example:

"extend"

overrides

object

Input fields to change for the new job, for example an edited prompt. Cannot change model.

Response

Idempotency replay — the existing job for this Idempotency-Key (no new charge).

string

required

Example:

"job_a1b2c3d4e5f6"

status

enum<string>

required

The status only moves forward: queued → running → completed, failed or cancelled. Everything a running job goes through — sending to the provider, uploading references, switching to another provider — is a stage of running; a job never goes back to queued. (Older API builds also reported submitting; treat it as running.)

awaiting_confirmation (multi-step pipelines only): the job finished a step that asks for review and waits for POST /jobs/{id}/confirm. It is not terminal.

Available options:

queued,

running,

awaiting_confirmation,

completed,

failed,

cancelled

stage

enum<string> | null

required

What the job is doing right now. null once the job is terminal, and while the job is awaiting_confirmation.

queued — waiting for a slot; no attempt yet
submitting — being sent to the provider
uploading_references — the provider is taking the reference files into its asset library (progress_message shows n/m)
rendering — the provider accepted the task and is generating
retrying — an attempt failed (the provider refused, failed or rate limited it); the job waits for its next attempt, usually on another provider. See attempts.
finalizing — the result is being saved and billed

Available options:

queued,

submitting,

uploading_references,

rendering,

retrying,

finalizing,

null

attempts

object[]

required

Every provider tried for this job, oldest first. provider / provider_model are the newest one.

Show child attributes

tool

string

required

Internal tool id (e.g. tool_2001a2b3c4d5 for video), not the tool_key. Do not compare it against GET /tools keys.

Example:

"tool_2001a2b3c4d5"

input

object

required

The request body as submitted (model, prompt, ...)

output

object | null

required

Canonical output envelope. Present only when the job is completed.

Show child attributes

error

string | null

required

Human-readable failure message. null unless the job failed or was cancelled.

progress_message

string | null

required

Example:

"stitching 3/8 (40%)"

progress

number | null

required

Fraction 0..1

progress_metadata

object | null

required

step_state

object | null

required

Multi-step pipeline jobs only: the current step and each step's status, intermediate output and cost. null for ordinary jobs.

Show child attributes

estimated_duration_ms

integer | null

required

estimated_cost_cents

integer | null

required

actual_cost_cents

integer | null

required

pricing

object

required

Structured pricing. 1 credit = 1 cent = $0.01.

Show child attributes

provider

string | null

required

Example:

"fal"

provider_model

string | null

required

Example:

"fal:flux_schnell"

provider_status

string | null

required

The provider's raw status string

provider_job_id

string | null

required

completed_by_provider_model_id

string | null

required

Provider model route that completed the job

last_attempt_provider_model_id

string | null

required

Provider model route of the most recent attempt

workspace_id

string | null

required

Folder the outputs are filed into (see X-Workspace-Id)

created_at

string<date-time>

required

started_at

string<date-time> | null

required

completed_at

string<date-time> | null

required

warnings

string[]

Present on creation responses when the request was adjusted (for example a resolution fallback)

urls

object

Lifecycle URLs (present on creation responses)

Show child attributes

Overview

Presets

Generation

Tools

Jobs

Files

Folders

Templates

Pricing & Billing

Analytics

Account

Re-run a finished pipeline job from a later step

Authorizations

Headers

Path Parameters

Body

Response