How much does the Pixverse v6 API cost?

Pixverse v6 API pricing is per-second by resolution, billed at 360p / 540p / 720p / 1080p tiers. Turning audio on raises the per-second rate at every tier. See current per-tier rates in the pricing table on this page. The bill is the per-second rate times your clip duration.

Which modes does the Pixverse v6 API support and how do I pick one?

There is no mode field — the Pixverse v6 API picks the mode from your request shape: a prompt alone is text-to-video; image_urls is image-to-video; a first_frame_image plus last_frame_image is a transition; img_references is multi-reference fusion; extend_from_task_id is video extend.

What resolutions and durations does the Pixverse v6 API support?

The Pixverse v6 API supports 360p, 540p, 720p, and 1080p. Duration accepts any integer from 1 to 15 seconds (default 5). The first/last-frame transition mode accepts only 5 or 8 seconds. Pricing scales linearly with duration.

How many reference images can multi-reference fusion take?

The Pixverse v6 API multi-reference fusion mode accepts 1 to 7 reference images in the img_references array. The API fuses subjects from each image into one clip; aspect ratio applies in this mode as it does in text-to-video.

Does the Pixverse v6 API generate audio?

Optionally. Audio defaults to off. Set audio to true in the request body and the Pixverse v6 API mixes a soundtrack into the clip — this raises the per-second rate. Leave it off for a silent video at the lower rate.

How does video extend work in the Pixverse v6 API?

Pass extend_from_task_id set to the task ID of one of your own completed pixverse-v6 videos, plus a prompt. The Pixverse v6 API continues the scene from where that clip ended. Chain extends to grow a longer sequence without re-rendering the whole shot.

Where is the full Pixverse v6 API reference?

The full Pixverse v6 API parameter list, error codes, and runnable cURL / Python / Node / Go examples live at /docs/pixverse-v6.

Is Pixverse v6 API free or paid?

Paid. Completed generations are charged at the rates in this page's pricing table. Eligible new accounts may receive promotional test credits; availability and amount are shown at signup or in the dashboard. Technical or provider failures are refunded automatically, except where this page documents a charged output-moderation block.

Does Pixverse v6 API require a monthly subscription?

No. Pricing is pay-as-you-go: $1 buys 1,000 credits and credits never expire. Cost scales with what you generate rather than with a recurring fee.

How do I get a Pixverse v6 API key?

Sign up and create a key in the dashboard, no card required. Pass it as a Bearer token in the Authorization header.

Pixverse v6 API — Five Video Modes in One Endpoint

The Pixverse v6 API turns a prompt, an image, a pair of keyframes, or up to seven references into a 1 to 15 second clip at 360p–1080p. One endpoint covers text-to-video, image-to-video, first/last-frame transitions, multi-reference fusion, and video extend — with optional generated audio.

Highlights: 1–15 s · up to 1080p · extend & multi-clip
Best for: Anime, effects-heavy shorts, extends
Input: Text, images, frames or references
Output: Video, optional audio

Input

Prompt*

≤ 5000 chars · required in every mode

Resolution

Default 540p

Duration (seconds)5

1 to 15 · default 5 · 5 or 8 only for first/last-frame

Aspect ratio

Default 16:9

Seed

0 to 2147483647 · default 0

Negative prompt

≤ 2048 chars

Audio

Default off

Watermark

Default off

Motion mode

normal

Multi-clip

Default off

Estimated cost~$0.138138 credits

Result

Try one of these prompts

What is the Pixverse v6 API?

Pixverse v6 is PixVerse's video generation model, exposed on reAPI as one async endpoint covering five modes: text-to-video, image-to-video, first/last-frame transition, multi-reference fusion with up to seven reference images, and extending an existing clip. The mode is implicit — whichever media fields you send picks it — and each request returns 1 to 15 seconds of video at 360p, 540p, 720p or 1080p across eight aspect ratios, with optional generated audio. Billing is per second, at a rate set by resolution and by whether audio is on.

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Multi-reference fusion clip from the Pixverse v6 API

Fuse multiple references into one shot with the Pixverse v6 API

Send 1 to 7 reference images and a prompt. The Pixverse v6 API fuses characters, outfits, and objects from each reference into a single coherent clip — keep a face from one image, a costume from another, and a prop from a third without a separate compositing pass.

Generate a clip

First/last-frame transition from the Pixverse v6 API

Smooth transitions between two frames with the Pixverse v6 API

Pass a first frame and a last frame and the Pixverse v6 API interpolates the motion between them. Stitch keyframes straight into a finished 5 or 8 second shot — useful for transformations, reveals, and product before/after spots.

Video extend output from the Pixverse v6 API

Extend a clip into a continuous scene with the Pixverse v6 API

Pass the task ID of a finished Pixverse v6 video and a new prompt; the API continues the scene from where it ended. Chain extends to build a longer sequence one beat at a time, without re-rendering the whole shot.

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost

$0.09292 credits

One 5-second sample at the cheapest tier.

Testing budget guide

Add credits

$10

≈ 108 tests

$50

≈ 543 tests

$100

≈ 1086 tests

Model	Category	Price
360p	No audio	$0.019 19 credits · 1 second
360p	With audio	$0.028 28 credits · 1 second
540p	No audio	$0.028 28 credits · 1 second
540p	With audio	$0.037 37 credits · 1 second
720p	No audio	$0.037 37 credits · 1 second
720p	With audio	$0.046 46 credits · 1 second
1080p	No audio	$0.074 74 credits · 1 second
1080p	With audio	$0.092 92 credits · 1 second

Why reAPI

Five modes, one endpoint

The Pixverse v6 API picks its mode from the fields you send. A prompt alone gives text-to-video; one image gives image-to-video; a first/last frame pair interpolates a transition; reference images trigger multi-reference fusion; a task ID extends an existing clip — all on the same /api/v1/videos/generations call, with the same authentication and the same task polling pattern.

Pricing by resolution × seconds

The Pixverse v6 API charges per second by resolution. Turning audio on raises the per-second rate; every other parameter is free. See current 360p / 540p / 720p / 1080p rates in the pricing table on this page. Failed jobs refund automatically.

Reference fusion and frame control

Beyond plain text-to-video, the Pixverse v6 API fuses up to seven reference images into one shot and interpolates between a first and last keyframe. That control lives in the request body — no extra endpoint, no model swap, no separate compositing step.

Pixverse v6 vs Runway Gen-3

Both turn text and images into short clips. Pixverse v6 leans into mode breadth — five input shapes on one endpoint, including multi-reference fusion and video extend — and per-second usage pricing. Here is how the two compare on publicly documented behavior.

Capability

Pixverse v6 on reAPI

Runway Gen-3

Input modes

Five on one endpoint: text-to-video, image-to-video, first/last-frame, multi-reference fusion, and video extend.

Text-to-video and image-to-video, plus separate features for extend and lip sync.

Multi-reference fusion

Fuses 1 to 7 reference images into one clip from a single request.

No documented multi-image fusion in the base text/image-to-video flow.

Pricing model

Pay-as-you-go per second by resolution; audio adds an uplift. No subscription required.

Credit-based plans, typically purchased through a subscription.

Resolution range

360p, 540p, 720p, and 1080p selectable per request.

Fixed output resolution tiers per plan.

Built-in audio

Optional generated soundtrack via a single audio flag in the request body.

Audio handled through a separate feature rather than the base generation call.

Integration

One REST endpoint, submit-and-poll, OpenAI-style API key — same pattern as every other reAPI model.

Dedicated API and console with its own request and polling shapes.

Comparison reflects publicly documented behavior at the time of writing. Model behavior and pricing can change; check the pricing card above and the API docs for current values.

Ship the Pixverse v6 API in three steps

step 01
Create an API key
Sign up and grab a key from the dashboard. Free credits cover your first Pixverse v6 API calls — no card required.
Open
step 02
Submit a video task
POST to /api/v1/videos/generations with model = pixverse-v6 and a prompt. The Pixverse v6 API returns a task ID immediately so your worker can move on.
Open
step 03
Poll the result
GET /api/v1/tasks/:id until status is completed. Download the Pixverse v6 API output and ship it.
Open

docs/api/pixverse-v6

API reference

Drop-in code and the full parameter table.

View full reference

curl -X POST https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "pixverse-v6",
    "prompt": "A neon-lit Tokyo alley at night, light rain, anamorphic flare",
    "size": "21:9",
    "resolution": "720p",
    "duration": 8
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

The Pixverse v6 API is an async video generation endpoint. One request body covers five modes — text-to-video, image-to-video, first/last-frame transition, multi-reference fusion, and video extend — and the API auto-routes the mode from the fields you attach.