PixVerse V6 Max is the high-quality variant of PixVerse V6. PixVerse V6 Max API generates video from text or one image with model pixverse-v6-max. Choose 1–15 seconds, 360p/540p/720p/1080p and optional native audio. Max focuses on these two workflows; PixVerse V6 remains available for transitions, fusion and extension.
76 / 5000 characters
Transparent pricing with no hidden fees. Pay only for what you use.
| Variant | Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|---|
pixverse-v6-max | 360P | 0.2133Credits(~$0.0213)/sec | 0.2027Credits(~$0.0203)/sec | 0.192Credits(~$0.0192)/sec | 0.2667Credits(~$0.0267)/sec | 20% |
| 360P+audio | 0.32Credits(~$0.032)/sec | 0.304Credits(~$0.0304)/sec | 0.288Credits(~$0.0288)/sec | 0.4Credits(~$0.04)/sec | 20% | |
| 540P | 0.32Credits(~$0.032)/sec | 0.304Credits(~$0.0304)/sec | 0.288Credits(~$0.0288)/sec | 0.4Credits(~$0.04)/sec | 20% | |
| 540P+audio | 0.3911Credits(~$0.0391)/sec | 0.3716Credits(~$0.0372)/sec | 0.352Credits(~$0.0352)/sec | 0.4889Credits(~$0.0489)/sec | 20% | |
| 720P | 0.3911Credits(~$0.0391)/sec | 0.3716Credits(~$0.0372)/sec | 0.352Credits(~$0.0352)/sec | 0.4889Credits(~$0.0489)/sec | 20% | |
| 720P+audio | 0.5333Credits(~$0.0533)/sec | 0.5067Credits(~$0.0507)/sec | 0.48Credits(~$0.048)/sec | 0.6667Credits(~$0.0667)/sec | 20% | |
| 1080P | 0.7822Credits(~$0.0782)/sec | 0.7431Credits(~$0.0743)/sec | 0.704Credits(~$0.0704)/sec | 0.9778Credits(~$0.0978)/sec | 20% | |
| 1080P+audio | 0.9956Credits(~$0.0996)/sec | 0.9458Credits(~$0.0946)/sec | 0.896Credits(~$0.0896)/sec | 1.2444Credits(~$0.1244)/sec | 20% |
* Actual costs are subject to final output.
Build text-to-video and image-to-video workflows with the PixVerse V6 Max video API. This high-quality PixVerse V6 variant turns a scene description or one product image into a short clip. Use pixverse-v6-max in your request and choose silent video or native audio to suit your application.
2
Generation modes
4
Resolutions
1–15s
Clip duration
—
Current savings
Call the PixVerse V6 Max API with model pixverse-v6-max. Copy a text-to-video or image-to-video example below; audio is omitted, so these examples generate silent video.
Store your key in APIMART_API_KEY and send it in the Authorization: Bearer header.
POST /v1/videos/generations with model pixverse-v6-max and the required inputs. Save the returned task ID.
Query GET /v1/tasks/{task_id} until completion, then read the video result. Inspect error details if the task fails.
See the APIMart documentation for API details.
curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "pixverse-v6-max",
"prompt": "A blue glass marble rolls across a clean white table in warm morning light, with a slow camera push-in",
"duration": 5,
"resolution": "540p",
"aspect_ratio": "16:9"
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "pixverse-v6-max",
"prompt": "A blue glass marble rolls across a clean white table in warm morning light, with a slow camera push-in",
"duration": 5,
"resolution": "540p",
"aspect_ratio": "16:9"
}
resp = requests.post(f"{API_BASE}/v1/videos/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["videos"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(10)
else:
raise TimeoutError(f"task {task_id} did not finish in time")curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "pixverse-v6-max",
"prompt": "Animate this product with gentle movement and a slow camera push-in",
"image_urls": [
"https://example.com/product.jpg"
],
"duration": 5,
"resolution": "540p"
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: pixverse-v6-max | Fixed model ID: pixverse-v6-max. |
prompt | string | Required | Default: — | Required in both modes: up to 5,000 characters for text-to-video and 2,048 for image-to-video. Empty or whitespace-only prompts are not accepted. |
image_urls | string[] | Optional | Default: — | Exactly one public HTTP(S) image URL for image-to-video. JPEG, PNG or WebP; under 20 MB, each side at most 10000 px. |
duration | integer | Optional | Default: 5 | Integer from 1 to 15 seconds; default 5. |
resolution | string | Optional | Default: 540p | 360p, 540p, 720p or 1080p; default 540p. The quality alias is accepted, but resolution takes precedence. Pixel dimensions follow the upstream model’s native output; use the dimensions actually returned. |
aspect_ratio | string | Optional | Default: 16:9 | Text only: 16:9, 9:16, 4:3, 3:4, 1:1, 2:3, 3:2 or 21:9. Image-to-video follows the image and ignores this field. |
audio | boolean | Optional | Default: false | Top-level true enables native audio at a higher rate; false or omission produces silent video. |
seed | integer | Optional | Default: — | Optional integer from 0 to 2147483647. |
Use the PixVerse V6 Max API to control the prompt, image, duration, output settings and sound in one request.
Build with the pixverse-v6-max API, from product image animation to short clips generated from text.
Use one APIMart API key to authenticate both text-to-video and image-to-video requests for pixverse-v6-max.
Sign in to APIMart, create an API key on the API Keys page and fund your balance before submitting paid video requests.
Choose text or one image, then set duration, resolution and audio. Review the live estimate before submitting.
Send POST /v1/videos/generations, save the task ID and query GET /v1/tasks/{task_id}.
Answers about the PixVerse V6 Max model, API keys, video settings and pricing.
PixVerse V6 Max is the high-quality V6 variant for text-to-video and single-image animation, called with model pixverse-v6-max. First/last-frame transitions, multi-image fusion and video extension use the separate pixverse-v6 model; they are not Max generation modes.
Choose 360p, 540p, 720p or 1080p and an integer duration from 1 to 15 seconds. Defaults are 540p and 5 seconds. Text generation supports eight ratios; image generation inherits the input image ratio. Pixel dimensions follow the upstream model’s native output; use the dimensions actually returned. Tested examples include 640×360 and 1108×832.
Provide exactly one publicly accessible HTTP(S) image URL. JPEG, PNG and WebP are supported, under 20 MB and at most 10000 px per side. Two or more images are rejected.
Required in both modes: up to 5,000 characters for text-to-video and 2,048 for image-to-video. Empty or whitespace-only prompts are not accepted.
PixVerse V6 Max API pricing depends on output duration, resolution and the audio setting. Multiply output seconds by the corresponding live per-second rate. Silent video is the default; top-level audio set to true enables a native soundtrack at the separate audio rate. Use the Max pricing table rather than the rates for PixVerse V6.
Submit POST /v1/videos/generations with model pixverse-v6-max, then query GET /v1/tasks/{task_id}. The playground keeps Max tasks separate from V6 and lets you reuse settings from generation records.
Sign in to APIMart and create a key on the API Keys page. Your PixVerse V6 Max API key is an APIMart credential: send it in the Authorization: Bearer header and set model to pixverse-v6-max. Keep the key on your server rather than in public browser code.
PixVerse V6 Max is the display name; pixverse-v6-max is the exact API model ID. Capitalization or hyphenated spellings such as Pixverse V6 Max and PixVerse-V6-Max are presentation variants, not extra model IDs. The shorter phrase PixVerse Max API omits the version, so check that you are requesting V6 Max. PixVerse V6 is a separate model.
Explore more models in the same category.

Kling V4
Kling 4.0 is an advanced AI video generation model that brings creative ideas to life with realistic motion, dynamic camera work, and precise visual control. With support for continuous videos up to 30 seconds and multiple reference inputs, it helps creators craft cinematic stories with greater flexibility.

ViduQ 4 Preview
Vidu Q4 Preview is ShengShu's image-to-video and reference-to-video model. Animate one first frame or combine up to 15 reference images and 3 audio clips into 3–16 second videos at up to 4K, with audio generated by default.

Wan 3.0 Video Prime
Wan 3.0 Prime is the Prime version of Alibaba Cloud's all-in-one Wan 3.0 video model, with general, first-and-last-frame and file or webpage modes and 2–30 second output.

Gemini Omni 1.1 Flash
Gemini Omni 1.1 Flash is a multimodal video model officially released by Google that supports rapid generation, natural language editing, and cinematic-quality visual control. This page connects to the official service through APIMart’s unified video API and uses separate pricing and task logs.