Veo 3.1 Extend

Overview

Veo 3.1 Extend continues an existing veo-3-1 video task with a new prompt. Use this page when you already have a completed Veo 3.1 taskId from APIXO and want to branch or lengthen the scene without starting from a fresh source prompt.

Capability	Value
Model ID	`veo-3-1-extend`
Mode	Video-to-video continuation
Source task	Existing APIXO `veo-3-1` `taskId`
Extend modes	`fast`, `quality`
Prompt length	1-10000 characters
Output	Video URL in `resultJson.resultUrls`

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/veo-3-1-extend`	Submit an extend task
`GET`	`/statusTask/veo-3-1-extend?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request extends a previous veo-3-1 task and returns a new extend taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/veo-3-1-extend" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "taskId": "task_id_from_previous_veo_3_1_generation",
      "mode": "fast",
      "prompt": "continue this scene with a smooth camera move and richer visual rhythm"
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "extend_task_12345678"
  }
}

Save this new taskId; use it with the status endpoint to retrieve the extended video.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/veo-3-1-extend?taskId=extend_task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "extend_task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "extend_task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/xxx.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965730929,
    "costTime": 120000
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "extend_task_12345678",
    "state": "failed",
    "failCode": "CONTENT_VIOLATION",
    "failMsg": "Content does not meet safety guidelines",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const videoUrls = payload.resultUrls;

Request body

Fast extend

{
  "request_type": "async",
  "input": {
    "taskId": "task_id_from_previous_veo_3_1_generation",
    "mode": "fast",
    "prompt": "continue the action into a tense chase through narrow streets"
  }
}

Quality extend

{
  "request_type": "async",
  "input": {
    "taskId": "task_id_from_previous_veo_3_1_generation",
    "mode": "quality",
    "prompt": "extend this scene into a dramatic sunset over the city skyline",
    "watermark": "BrandName",
    "seed": 1234
  }
}

Parameters

request_type

string

default:"async"

required

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

callback_url

string

Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.

input

object

required

Veo 3.1 Extend input parameters.

Show properties

taskId

string

required

APIXO task ID returned by a previous /generateTask/veo-3-1 request. The task must exist, be usable for extension, and belong to veo-3-1.

mode

string

required

Extend mode. Supported values: fast, quality.

prompt

string

required

Continuation prompt for the extended scene. Supports 1-10000 characters.

watermark

string

Optional watermark text for the extended video.

seed

integer

Optional random seed. Omit this field if you do not need seed control.

Use the data.taskId returned by /generateTask/veo-3-1. External task IDs cannot be used directly.

Response format

Submit task response

POST /generateTask/veo-3-1-extend returns a new extend task ID when the task is accepted:

code

integer

API status code. 200 means the task was accepted.

message

string

Human-readable status message.

data.taskId

string

Unique extend task identifier used with the status endpoint.

Status response fields

taskId

string

Unique extend task identifier.

state

string

Current task state: pending, processing, success, or failed.

resultJson

string

JSON string containing the extended video URLs. Present when state is success.

failCode

string

Machine-readable failure code. Present when state is failed.

failMsg

string

Human-readable failure message. Present when state is failed.

createTime

integer

Task creation timestamp in Unix milliseconds.

completeTime

integer

Task completion timestamp in Unix milliseconds. Present after completion.

costTime

integer

Processing duration in milliseconds. Present after completion.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/veo-3-1-extend" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "taskId": "task_id_from_previous_veo_3_1_generation",
      "mode": "quality",
      "prompt": "continue the shot with calmer pacing and a wide establishing view",
      "seed": 1234
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Veo 3.1 Extend is billed per extended video task.

Billing unit	Starting APIXO price
Extended video	`$0.20 / video`

For current route and market comparison pricing, see Pricing.

Latency and polling

Veo 3.1 Extend is an asynchronous video workflow. Actual latency may vary by extend mode, prompt complexity, upstream queue load, and result storage time.

Workflow	Recommended first poll	Poll interval
`fast`	30s after task creation	10s
`quality`	60s after task creation	10s

For high-concurrency production workloads, use callback mode to avoid frequent polling.

Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, missing required parameter, unsupported mode, or unusable source task ID	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error	Retry with backoff
`502`	Upstream service error	Retry with backoff
`504`	Upstream timeout	Retry or use callback mode for long-running jobs

Task failure codes

Fail code	Meaning	What to do
`TASKID_ERROR`	The source task ID was not found, expired, or does not belong to `veo-3-1`	Use a valid `data.taskId` from a previous `veo-3-1` task
`CONTENT_VIOLATION`	The continuation prompt failed safety checks	Change the prompt
`INVALID_PARAMETER`	A model parameter is unsupported or malformed	Check `taskId`, `mode`, `prompt`, `watermark`, and `seed`
`INSUFFICIENT_BALANCE`	The account does not have enough balance for the task	Add balance before retrying
`UPSTREAM_ERROR`	Upstream-side failure	Retry with backoff or try another route
`TIMEOUT`	Generation did not finish in time	Retry, reduce prompt complexity, or use callback mode

See Error Codes for the full error reference.

Documentation Index

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Fast extend

​Quality extend

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Task failure codes

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Fast extend

Quality extend

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Task failure codes

Related links