TokenLX — One API for 245+ AI Models

HappyHouse video edit restyles source videos asynchronously through `/edit/video/tasks`.

Key strengths

Prompted style edit
Async task polling
Resolution controls

Use cases

Style transfer
Short-video restyle
Creative edits

videoeditstyle

Alibaba's alibaba/happyhouse-1.0-video-edit is a high-fidelity video generation model. It supports text-to-video and image-to-video workflows with configurable duration, aspect ratio, and resolution, plus first-frame and last-frame control for guided scene composition.

Generates cinematic clips with consistent motion, camera control, and optional native audio. Billed per second of generated content.

alibaba/happyhouse-1.0-video-edit is fully OpenAI-compatible — drop in your existing OpenAI Python or Node SDK and switch `baseURL` to `https://api.tokenlx.ai`. TokenLX transparently routes your requests to the optimal provider endpoint while preserving streaming, function-calling, and structured-output semantics.

Performance

Compare different providers across TokenLX · All locations.

Throughput

tok/s

Latency

131

E2E Latency

200

Tool Call Errors

0.07

Output Errors

0.38

Time to First Token

101

Effective Pricing

Pricing is shown by the model billing method, using per-call or per-second prices and resolution tiers.

Per second

$0.13

Per duration

Resolution pricing · with audio

720P

$0.13

1080P

$0.24

Recent activity

Total usage per day on TokenLX (last 30 days).

Prompt

138.00M

Completion

310.50M

30d ago15d agotoday

Sample code & API

TokenLX normalizes requests and responses across providers. Use any OpenAI SDK or our native SDK.

import requests
import time

headers = {
    "Authorization": "Bearer sk-aihub-...",
    "Content-Type": "application/json",
}

# Create video edit task
create = requests.post(
    "https://api.tokenlx.ai/v1/edit/video/tasks",
    headers=headers,
    json={
        "model": "happyhouse-1.0-video-edit",
        "url": "https://example.com/source.mp4",
        "extendedParameter": '{"prompt":"将视频风格改为水彩插画风格。","resolution":"720P","audio_setting":"origin"}',
    },
).json()
task_id = create.get("taskId") or create.get("task_id")

# Poll result: GET https://api.tokenlx.ai/v1/edit/video/tasks/{taskId}?model=happyhouse-1.0-video-edit
while True:
    result = requests.get(
        f"https://api.tokenlx.ai/v1/edit/video/tasks/{task_id}?model=happyhouse-1.0-video-edit",
        headers=headers,
    ).json()
    print(result)
    if result.get("status") in ("success", "failed", "completed", "succeeded"):
        break
    time.sleep(8)

Replace sk-aihubrouter-… with your key from the dashboard.

Parameter Reference

Async Workflow

Create task

POST /v1/aigc/video/tasks

Poll result

GET /v1/aigc/video/tasks/{taskId}?model=happyhouse-1.0-video-edit

Recommended poll interval: 5–15sTask ID validity: 24h

Response is raw upstream JSON passthrough — fields vary by channel.

Parameter	Type	Required	Description
model	string	Yes	Model name
prompt	string	Yes	Video description prompt
duration	int	No	Duration in seconds (≤15s)
aspectRatio	string	No	Aspect ratio `16:99:161:1`
resolution	string	No	Output resolution `720P1080P`
seed	int	No	Random seed — fixed value produces reproducible results
referenceImageUrls	array	Image-to-video	Reference image URLs. Formats: JPEG/JPG/PNG/BMP/WEBP; Size: ≤10MB. For reference video (r2v) mode, supply ≥2 images and reference them as "图1" "图2" in prompt.
videoInputMode	string	No	Input mode: first_frame (1 image) or reference (≥2 images). Auto-inferred if omitted. `first_framereference`

modelstringYes

Model name

promptstringYes

Video description prompt

durationintNo

Duration in seconds (≤15s)

aspectRatiostringNo

Aspect ratio

16:99:161:1

resolutionstringNo

Output resolution

720P1080P

seedintNo

Random seed — fixed value produces reproducible results

referenceImageUrlsarrayImage-to-video

Reference image URLs. Formats: JPEG/JPG/PNG/BMP/WEBP; Size: ≤10MB. For reference video (r2v) mode, supply ≥2 images and reference them as "图1" "图2" in prompt.

videoInputModestringNo

Input mode: first_frame (1 image) or reference (≥2 images). Auto-inferred if omitted.

first_framereference

Sample code & API

TokenLX normalizes requests and responses across providers. Use any OpenAI SDK or our native SDK.

import requests
import time

headers = {
    "Authorization": "Bearer sk-aihub-...",
    "Content-Type": "application/json",
}

# Create video edit task
create = requests.post(
    "https://api.tokenlx.ai/v1/edit/video/tasks",
    headers=headers,
    json={
        "model": "happyhouse-1.0-video-edit",
        "url": "https://example.com/source.mp4",
        "extendedParameter": '{"prompt":"将视频风格改为水彩插画风格。","resolution":"720P","audio_setting":"origin"}',
    },
).json()
task_id = create.get("taskId") or create.get("task_id")

# Poll result: GET https://api.tokenlx.ai/v1/edit/video/tasks/{taskId}?model=happyhouse-1.0-video-edit
while True:
    result = requests.get(
        f"https://api.tokenlx.ai/v1/edit/video/tasks/{task_id}?model=happyhouse-1.0-video-edit",
        headers=headers,
    ).json()
    print(result)
    if result.get("status") in ("success", "failed", "completed", "succeeded"):
        break
    time.sleep(8)

Replace sk-aihubrouter-… with your key from the dashboard.

Parameter Reference

Async Workflow

Create task

POST /v1/aigc/video/tasks

Poll result

GET /v1/aigc/video/tasks/{taskId}?model=happyhouse-1.0-video-edit

Recommended poll interval: 5–15sTask ID validity: 24h

Response is raw upstream JSON passthrough — fields vary by channel.

Parameter	Type	Required	Description
model	string	Yes	Model name
prompt	string	Yes	Video description prompt
duration	int	No	Duration in seconds (≤15s)
aspectRatio	string	No	Aspect ratio `16:99:161:1`
resolution	string	No	Output resolution `720P1080P`
seed	int	No	Random seed — fixed value produces reproducible results
referenceImageUrls	array	Image-to-video	Reference image URLs. Formats: JPEG/JPG/PNG/BMP/WEBP; Size: ≤10MB. For reference video (r2v) mode, supply ≥2 images and reference them as "图1" "图2" in prompt.
videoInputMode	string	No	Input mode: first_frame (1 image) or reference (≥2 images). Auto-inferred if omitted. `first_framereference`

modelstringYes

Model name

promptstringYes

Video description prompt

durationintNo

Duration in seconds (≤15s)

aspectRatiostringNo

Aspect ratio

16:99:161:1

resolutionstringNo

Output resolution

720P1080P

seedintNo

Random seed — fixed value produces reproducible results

referenceImageUrlsarrayImage-to-video

Reference image URLs. Formats: JPEG/JPG/PNG/BMP/WEBP; Size: ≤10MB. For reference video (r2v) mode, supply ≥2 images and reference them as "图1" "图2" in prompt.

videoInputModestringNo

Input mode: first_frame (1 image) or reference (≥2 images). Auto-inferred if omitted.

first_framereference

alibaba/happyhouse-1.0-video-edit

Key strengths

Use cases

Performance

Effective Pricing

Recent activity

Sample code & API

Parameter Reference

More models from Alibaba

alibaba/happyhouse-1.0-video-edit

Key strengths

Use cases

Performance

Effective Pricing

Recent activity

Sample code & API

Parameter Reference

More models from Alibaba