PixVerse V6 API

About PixVerse V6

The PixVerse V6 API exposes four video jobs under the pixverse/v6 prefix: text-to-video as the default, plus image-to-video, reference-to-video and video-extend. Each createTask call returns a taskId at once, and the finished MP4 arrives when the render completes. Reach for it when your product needs a clip whose length you can set to the second, and when one integration should cover several starting points, from a sentence to a still to a clip that already exists.

Call it with the model name pixverse/v6/text-to-video on POST /jobs/createTask, from $0.111.

Introduction

PixVerse V6 Text to video turns a written brief into a clip of 1 to 15 seconds at 360p, 540p, 720p or 1080p, in eight aspect ratios from 16:9 to 9:16 and 21:9. Describe the subject, the action and the camera; camera moves written in the prompt are followed, and PixVerse says V6 understands 20+ cinematic lens and camera controls from the prompt. Switch generate_audio on and the model generates sound with the picture.

Choose a PixVerse V6 mode by starting material

Key features

One paragraph, more than one framing

In our test a single paragraph about a laughing driver in a vintage teal convertible opened on a close shot of her with the scarf flying, then the camera rose to a wide aerial of the car on a cliff road above the ocean. The prompt asked for the drone to pull back and rise; the cut from close-up to aerial came from the model.

A multi-shot switch

shot_type is single by default. Set multi to let the model cut the clip into several shots.

Eight aspect ratios

16:9 (default), 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 and 21:9.

Sound when you want it

generate_audio is off by default. On, the model generates ambience, effects, music and any dialogue you write in quotes.

Four resolutions

360p, 540p, 720p (default) and 1080p. Our test clip was 540p, 1024x576, and took about 41 seconds of model time for 5 seconds of video.

Request parameters

Pricing

Prices are in USD. The API uses a separate USD balance. Website credits cannot be used or transferred to it, and API funds cannot be transferred to website credits. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

Use cases

Opening and establishing shots

Write the place, the light, one camera move and the look, and you have a shot to open a scene with. Our cliff-road example does exactly that in one paragraph.

Short scenes with a spoken line

Switch audio on, describe the action and put the line in quotes. Name the ambience you want in the same prompt.

Vertical and ultrawide framing

Choose 9:16, 3:4 or 2:3 for vertical clips, or 21:9 for ultrawide.

Prompt guide & pro tips

Write it in the order it happens

Place and light first, then the subject and wardrobe, the action, the camera move and the look. Our example reads: golden hour on a cliffside highway, the car and the driver, the drone pulling back and rising, a warm 35mm film look.

Write the camera move

Camera moves you put in the prompt are followed, so name them: "the drone pulls back and rises", "slow orbit", "handheld push-in".

Compare with a seed

seed keeps runs comparable while you change one thing at a time. It does not guarantee identical frames.

API quick start

Call the PixVerse V6 API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls use your separate USD balance.
2. Send the request. POST /jobs/createTask with model pixverse/v6/text-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "pixverse/v6/text-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration_seconds": 5,
    "shot_type": "single"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

What to build with the PixVerse V6 API

• A social clip generator that takes a sentence and a length from the form and sends duration_seconds and resolution straight into createTask.
• A product-video tool that accepts a first frame and an optional last_image_url, so the shot opens and closes on images the customer approved.
• A creator app that stores named elements for each brand character and calls reference-to-video with the same element list for every campaign.
• A serial-content feature that chains video-extend calls, feeding the output file of one job in as video_url for the next.

PixVerse V6 parameter notes

• duration_seconds is a whole number from 1 to 15 and defaults to 5. Validate it in your form before createTask, because the endpoint accepts integers only within that range.
• resolution takes 360p, 540p, 720p (the default) or 1080p. The per-second rate rises at each tier, so 540p is a sensible default for previews.
• generate_audio defaults to false. Turning it on raises the rate for every resolution, so show the user the price difference before they switch it on.
• shot_type is single (the default) or multi. Multi lets the model cut between shots. It does not combine with last_image_url on image-to-video.
• aspect_ratio takes eight values, 16:9 by default, through 9:16 and 21:9. image-to-video has no aspect_ratio field, because the frame of image_url decides the shape of the output.
• reference-to-video takes elements, an array of one to seven objects with a name of 1 to 30 characters, an image_url and a role of subject or background. Write @name in the prompt followed by a space; in our tests a comma directly after the name, as in @trailer, was rejected.
• seed takes a whole number from 0 to 2147483647. It is useful for comparing one change at a time, but it does not guarantee identical frames.
• video-extend returns your source clip followed by duration_seconds of new footage in one file. Only the new seconds are billed.

How PixVerse V6 API pricing adds up

PixVerse V6 is billed in USD per second of output, and the rate depends on the resolution and on the sound switch. Without sound the rate is $0.0222 per second at 360p, $0.0311 at 540p, $0.040 at 720p and $0.080 at 1080p. With sound on it is $0.0311, $0.040, $0.0533 and $0.1022 for the same tiers. A five-second 720p clip with sound comes to about $0.27. Failed or declined requests are not charged, and API usage is paid from your separate API balance.

• generate_audio false · resolution 360p, 5-second clip: $0.111 each, $11.10 for 100 clips
• generate_audio true · resolution 1080p, 5-second clip: $0.511 each, $51.10 for 100 clips

Async jobs, webhooks and rate limits

Every PixVerse V6 request is asynchronous: createTask returns a taskId straight away, and the result arrives when the job finishes. Poll GET /jobs/recordInfo every few seconds, or pass a public https callBackUrl and verify the X-Webhook-Signature header (HMAC-SHA256 over taskId, timestamp and the body hash) before trusting the payload. Each account gets 1,000 write requests per 10 seconds; a 429 carries Retry-After. Send an Idempotency-Key with createTask so a retried request for pixverse/v6/text-to-video never runs or bills twice.

Common PixVerse V6 API errors

PixVerse V6 API questions

All PixVerse models

PixVerse V6 Max is the higher tier for text and image to video with richer detail, at a higher per-second price. V6 adds references, transitions and extensions.

• PixVerse V6 Max APIPixVerse's top tier: 1080p clips with optional soundFrom $0.133 for a 5-second clip
• PixVerse V6 Effects API50 ready-made effect templates that turn a photo into a themed clipFrom $0.0222 per second
• PixVerse V6 APIClips of 1 to 15 seconds up to 1080p, with transitions, references and extensionsFrom $0.111 for a 5-second clip

Other video APIs

• MiniMax H3 APIExpressive clips with audio, up to 30 seconds or 2KFrom $0.125 for a 5-second clip
• Kling O3 APIKling’s unified model: create, animate, reference and edit up to 4KFrom $0.336 for a 5-second clip
• MiniMax H3 Max APIFast clips with ambience, effects and musicFrom $0.25 for a 5-second clip
• LTX 2.5 APILong 20-second takes up to 4K with a soundtrackFrom $0.45 for a 5-second clip

More about PixVerse V6

Try it

PixVerse V6 AI Video Generator onlineCreate videos with PixVerse V6 in PopNow

Endpoints

PixVerse V6 · Image to VideoPixVerse V6 · Reference to VideoPixVerse V6 · Extend Video

Docs

PixVerse V6 model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage to video guide for the PopNow APIWebhooks: get PixVerse V6 results without polling